Run ddc5aa24

Name: gmod-bench run ddc5aa24-4d6c-4889-9348-24344c06a4ec
Creator: gmod-bench
License: https://github.com/Iydah/gmod-bench/blob/main/LICENSE

Jul 11, 2026, 07:43

Codex · 31 models · repeat ×1

ddc5aa24-4d6c-4889-9348-24344c06a4ec

Fixtures

1,178

Attempts

Models

13m

Duration

Codex×1 repeat

Downloads

Audit pack

Results

31 models

#	Adapter	Model	Think	Pass %	Cover %	Score	Outcomes	Time
1	Codex	gpt-5.5	Medium	97.2%	94.7%	93.4%	35/1/0/2	15.1s
#1 gpt-5.5 Medium Codex Pass rate97.2% 35 pass · 36 scored Coverage94.7% 36 / 38 evidence-bearing Verified score93.4% 95% interval — · 1 run(s) pass@k97.2% 35/38 fixtures ever solved Outcome mix Pass35 Partial1 Wrong0 Invalid output2 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored36 Passed35 Fixtures solved35/38 Run facts Avg time 15.1s Repeat Single-shot Evidence share 36/38 (94.7%) Verified runs 1 95% interval — Raw label codex/gpt-5.5@medium Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 35/38 passed in linked run perf-find-ents-nearperf-string-table-concatperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-angle-zeroperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
2	Codex	gpt-5.6-luna	High	97.2%	94.7%	93.4%	35/1/0/2	15.6s
#2 gpt-5.6-luna High Codex Pass rate97.2% 35 pass · 36 scored Coverage94.7% 36 / 38 evidence-bearing Verified score93.4% 95% interval — · 1 run(s) pass@k97.2% 35/38 fixtures ever solved Outcome mix Pass35 Partial1 Wrong0 Invalid output2 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored36 Passed35 Fixtures solved35/38 Run facts Avg time 15.6s Repeat Single-shot Evidence share 36/38 (94.7%) Verified runs 1 95% interval — Raw label codex/gpt-5.6-luna@high Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 35/38 passed in linked run perf-find-ents-nearperf-string-table-concatplayer-iteratorents-iteratorhook-addisvalidnet-receiversperf-angle-zeroperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-looking-atperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-x
3	Codex	gpt-5.6-luna	Extra High	97.2%	94.7%	93.4%	35/1/0/2	18.3s
#3 gpt-5.6-luna Extra High Codex Pass rate97.2% 35 pass · 36 scored Coverage94.7% 36 / 38 evidence-bearing Verified score93.4% 95% interval — · 1 run(s) pass@k97.2% 35/38 fixtures ever solved Outcome mix Pass35 Partial1 Wrong0 Invalid output2 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored36 Passed35 Fixtures solved35/38 Run facts Avg time 18.3s Repeat Single-shot Evidence share 36/38 (94.7%) Verified runs 1 95% interval — Raw label codex/gpt-5.6-luna@xhigh Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 35/38 passed in linked run perf-find-ents-nearperf-string-table-concatperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-angle-zeroperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
4	Codex	gpt-5.6-sol	Max	91.9%	97.4%	92.1%	34/2/1/1	18.4s
#4 gpt-5.6-sol Max Codex Pass rate91.9% 34 pass · 37 scored Coverage97.4% 37 / 38 evidence-bearing Verified score92.1% 95% interval — · 1 run(s) pass@k91.9% 34/38 fixtures ever solved Outcome mix Pass34 Partial2 Wrong1 Invalid output1 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored37 Passed34 Fixtures solved34/38 Run facts Avg time 18.4s Repeat Single-shot Evidence share 37/38 (97.4%) Verified runs 1 95% interval — Raw label codex/gpt-5.6-sol@max Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 34/38 passed in linked run perf-string-table-concatperf-angle-zeroperf-find-ents-nearperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
5	Codex	gpt-5.4-mini	High	89.2%	97.4%	90.8%	33/3/1/1	9.7s
#5 gpt-5.4-mini High Codex Pass rate89.2% 33 pass · 37 scored Coverage97.4% 37 / 38 evidence-bearing Verified score90.8% 95% interval — · 1 run(s) pass@k89.2% 33/38 fixtures ever solved Outcome mix Pass33 Partial3 Wrong1 Invalid output1 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored37 Passed33 Fixtures solved33/38 Run facts Avg time 9.7s Repeat Single-shot Evidence share 37/38 (97.4%) Verified runs 1 95% interval — Raw label codex/gpt-5.4-mini@high Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 33/38 passed in linked run perf-string-table-concatperf-angle-zeroperf-find-ents-nearperf-looking-atplayer-iteratorents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-x
6	Codex	gpt-5.6-sol	High	89.2%	97.4%	90.8%	33/3/1/1	13.3s
#6 gpt-5.6-sol High Codex Pass rate89.2% 33 pass · 37 scored Coverage97.4% 37 / 38 evidence-bearing Verified score90.8% 95% interval — · 1 run(s) pass@k89.2% 33/38 fixtures ever solved Outcome mix Pass33 Partial3 Wrong1 Invalid output1 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored37 Passed33 Fixtures solved33/38 Run facts Avg time 13.3s Repeat Single-shot Evidence share 37/38 (97.4%) Verified runs 1 95% interval — Raw label codex/gpt-5.6-sol@high Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 33/38 passed in linked run perf-string-table-concatperf-angle-zeroperf-find-ents-nearperf-for-vs-whileperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
7	Codex	gpt-5.6-sol	Low	89.2%	97.4%	90.8%	33/3/1/1	7.5s
#7 gpt-5.6-sol Low Codex Pass rate89.2% 33 pass · 37 scored Coverage97.4% 37 / 38 evidence-bearing Verified score90.8% 95% interval — · 1 run(s) pass@k89.2% 33/38 fixtures ever solved Outcome mix Pass33 Partial3 Wrong1 Invalid output1 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored37 Passed33 Fixtures solved33/38 Run facts Avg time 7.5s Repeat Single-shot Evidence share 37/38 (97.4%) Verified runs 1 95% interval — Raw label codex/gpt-5.6-sol@low Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 33/38 passed in linked run perf-string-table-concatperf-angle-zeroperf-find-ents-nearperf-for-vs-whileperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
8	Codex	gpt-5.6-sol	Medium	89.2%	97.4%	90.8%	33/3/1/1	9.4s
#8 gpt-5.6-sol Medium Codex Pass rate89.2% 33 pass · 37 scored Coverage97.4% 37 / 38 evidence-bearing Verified score90.8% 95% interval — · 1 run(s) pass@k89.2% 33/38 fixtures ever solved Outcome mix Pass33 Partial3 Wrong1 Invalid output1 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored37 Passed33 Fixtures solved33/38 Run facts Avg time 9.4s Repeat Single-shot Evidence share 37/38 (97.4%) Verified runs 1 95% interval — Raw label codex/gpt-5.6-sol@medium Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 33/38 passed in linked run perf-string-table-concatperf-angle-zeroperf-find-ents-nearperf-for-vs-whileperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
9	Codex	gpt-5.6-terra	Medium	89.2%	97.4%	90.8%	33/3/1/1	18.9s
#9 gpt-5.6-terra Medium Codex Pass rate89.2% 33 pass · 37 scored Coverage97.4% 37 / 38 evidence-bearing Verified score90.8% 95% interval — · 1 run(s) pass@k89.2% 33/38 fixtures ever solved Outcome mix Pass33 Partial3 Wrong1 Invalid output1 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored37 Passed33 Fixtures solved33/38 Run facts Avg time 18.9s Repeat Single-shot Evidence share 37/38 (97.4%) Verified runs 1 95% interval — Raw label codex/gpt-5.6-terra@medium Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 33/38 passed in linked run perf-string-table-concatperf-angle-zeroperf-find-ents-nearperf-looking-atperf-ply-table-indexents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
10	Codex	gpt-5.6-terra	Extra High	89.2%	97.4%	90.8%	33/3/1/1	13.3s
#10 gpt-5.6-terra Extra High Codex Pass rate89.2% 33 pass · 37 scored Coverage97.4% 37 / 38 evidence-bearing Verified score90.8% 95% interval — · 1 run(s) pass@k89.2% 33/38 fixtures ever solved Outcome mix Pass33 Partial3 Wrong1 Invalid output1 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored37 Passed33 Fixtures solved33/38 Run facts Avg time 13.3s Repeat Single-shot Evidence share 37/38 (97.4%) Verified runs 1 95% interval — Raw label codex/gpt-5.6-terra@xhigh Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 33/38 passed in linked run perf-string-table-concatperf-angle-zeroperf-find-ents-nearperf-looking-atperf-steamid-cacheents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
11	Codex	gpt-5.6-luna	Medium	97.1%	92.1%	89.5%	34/0/1/3	7.9s
#11 gpt-5.6-luna Medium Codex Pass rate97.1% 34 pass · 35 scored Coverage92.1% 35 / 38 evidence-bearing Verified score89.5% 95% interval — · 1 run(s) pass@k97.1% 34/38 fixtures ever solved Outcome mix Pass34 Partial0 Wrong1 Invalid output3 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored35 Passed34 Fixtures solved34/38 Run facts Avg time 7.9s Repeat Single-shot Evidence share 35/38 (92.1%) Verified runs 1 95% interval — Raw label codex/gpt-5.6-luna@medium Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 34/38 passed in linked run perf-find-ents-nearperf-seq-tablesperf-string-table-concatperf-angle-zeroents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-looking-atperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
12	Codex	gpt-5.6-sol	Extra High	89.2%	97.4%	89.5%	33/2/2/1	15.4s
#12 gpt-5.6-sol Extra High Codex Pass rate89.2% 33 pass · 37 scored Coverage97.4% 37 / 38 evidence-bearing Verified score89.5% 95% interval — · 1 run(s) pass@k89.2% 33/38 fixtures ever solved Outcome mix Pass33 Partial2 Wrong2 Invalid output1 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored37 Passed33 Fixtures solved33/38 Run facts Avg time 15.4s Repeat Single-shot Evidence share 37/38 (97.4%) Verified runs 1 95% interval — Raw label codex/gpt-5.6-sol@xhigh Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 33/38 passed in linked run perf-string-table-concatperf-angle-zeroperf-table-hasvalueperf-find-ents-nearperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
13	Codex	gpt-5.6-terra	Max	89.2%	97.4%	89.5%	33/2/2/1	25.1s
#13 gpt-5.6-terra Max Codex Pass rate89.2% 33 pass · 37 scored Coverage97.4% 37 / 38 evidence-bearing Verified score89.5% 95% interval — · 1 run(s) pass@k89.2% 33/38 fixtures ever solved Outcome mix Pass33 Partial2 Wrong2 Invalid output1 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored37 Passed33 Fixtures solved33/38 Run facts Avg time 25.1s Repeat Single-shot Evidence share 37/38 (97.4%) Verified runs 1 95% interval — Raw label codex/gpt-5.6-terra@max Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 33/38 passed in linked run perf-string-table-concatperf-angle-zeroperf-hudpaint-cacheperf-find-ents-nearperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
14	Codex	gpt-5.4	Medium	91.7%	94.7%	89.5%	33/2/1/2	15.0s
#14 gpt-5.4 Medium Codex Pass rate91.7% 33 pass · 36 scored Coverage94.7% 36 / 38 evidence-bearing Verified score89.5% 95% interval — · 1 run(s) pass@k91.7% 33/38 fixtures ever solved Outcome mix Pass33 Partial2 Wrong1 Invalid output2 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored36 Passed33 Fixtures solved33/38 Run facts Avg time 15.0s Repeat Single-shot Evidence share 36/38 (94.7%) Verified runs 1 95% interval — Raw label codex/gpt-5.4@medium Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 33/38 passed in linked run perf-find-ents-nearperf-string-table-concatperf-darkrpvarperf-angle-zeroperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-config-varperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
15	Codex	gpt-5.5	Extra High	91.7%	94.7%	89.5%	33/2/1/2	13.6s
#15 gpt-5.5 Extra High Codex Pass rate91.7% 33 pass · 36 scored Coverage94.7% 36 / 38 evidence-bearing Verified score89.5% 95% interval — · 1 run(s) pass@k91.7% 33/38 fixtures ever solved Outcome mix Pass33 Partial2 Wrong1 Invalid output2 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored36 Passed33 Fixtures solved33/38 Run facts Avg time 13.6s Repeat Single-shot Evidence share 36/38 (94.7%) Verified runs 1 95% interval — Raw label codex/gpt-5.5@xhigh Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 33/38 passed in linked run perf-find-ents-nearperf-string-table-concatperf-ply-table-indexperf-angle-zeroperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
16	Codex	gpt-5.6-luna	Max	91.7%	94.7%	89.5%	33/2/1/2	16.8s
#16 gpt-5.6-luna Max Codex Pass rate91.7% 33 pass · 36 scored Coverage94.7% 36 / 38 evidence-bearing Verified score89.5% 95% interval — · 1 run(s) pass@k91.7% 33/38 fixtures ever solved Outcome mix Pass33 Partial2 Wrong1 Invalid output2 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored36 Passed33 Fixtures solved33/38 Run facts Avg time 16.8s Repeat Single-shot Evidence share 36/38 (94.7%) Verified runs 1 95% interval — Raw label codex/gpt-5.6-luna@max Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 33/38 passed in linked run perf-find-ents-nearperf-string-table-concatperf-angle-zeroperf-looking-atplayer-iteratorents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-x
17	Codex	gpt-5.4-mini	Extra High	88.9%	94.7%	88.2%	32/3/1/1	37.0s
#17 gpt-5.4-mini Extra High Codex Pass rate88.9% 32 pass · 36 scored Coverage94.7% 36 / 38 evidence-bearing Verified score88.2% 95% interval — · 1 run(s) pass@k88.9% 32/38 fixtures ever solved Outcome mix Pass32 Partial3 Wrong1 Invalid output1 Harness1 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored36 Passed32 Fixtures solved32/38 Run facts Avg time 37.0s Repeat Single-shot Evidence share 36/38 (94.7%) Verified runs 1 95% interval — Raw label codex/gpt-5.4-mini@xhigh Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 32/38 passed in linked run perf-ply-table-indexperf-string-table-concatperf-angle-zeroperf-find-ents-nearperf-looking-atplayer-iteratorents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-x
18	Codex	gpt-5.4-mini	Low	88.9%	94.7%	88.2%	32/3/1/2	12.5s
#18 gpt-5.4-mini Low Codex Pass rate88.9% 32 pass · 36 scored Coverage94.7% 36 / 38 evidence-bearing Verified score88.2% 95% interval — · 1 run(s) pass@k88.9% 32/38 fixtures ever solved Outcome mix Pass32 Partial3 Wrong1 Invalid output2 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored36 Passed32 Fixtures solved32/38 Run facts Avg time 12.5s Repeat Single-shot Evidence share 36/38 (94.7%) Verified runs 1 95% interval — Raw label codex/gpt-5.4-mini@low Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 32/38 passed in linked run perf-seq-tablesperf-string-table-concatperf-angle-zeroperf-find-ents-nearperf-looking-atplayer-iteratorents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-x
19	Codex	gpt-5.5	Low	88.9%	94.7%	88.2%	32/3/1/2	9.5s
#19 gpt-5.5 Low Codex Pass rate88.9% 32 pass · 36 scored Coverage94.7% 36 / 38 evidence-bearing Verified score88.2% 95% interval — · 1 run(s) pass@k88.9% 32/38 fixtures ever solved Outcome mix Pass32 Partial3 Wrong1 Invalid output2 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored36 Passed32 Fixtures solved32/38 Run facts Avg time 9.5s Repeat Single-shot Evidence share 36/38 (94.7%) Verified runs 1 95% interval — Raw label codex/gpt-5.5@low Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 32/38 passed in linked run perf-find-ents-nearperf-string-table-concatperf-darkrpvarperf-angle-zeroperf-for-vs-whileperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-config-varperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
20	Codex	gpt-5.6-luna	Low	88.9%	94.7%	86.8%	32/2/2/2	8.9s
#20 gpt-5.6-luna Low Codex Pass rate88.9% 32 pass · 36 scored Coverage94.7% 36 / 38 evidence-bearing Verified score86.8% 95% interval — · 1 run(s) pass@k88.9% 32/38 fixtures ever solved Outcome mix Pass32 Partial2 Wrong2 Invalid output2 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored36 Passed32 Fixtures solved32/38 Run facts Avg time 8.9s Repeat Single-shot Evidence share 36/38 (94.7%) Verified runs 1 95% interval — Raw label codex/gpt-5.6-luna@low Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 32/38 passed in linked run perf-seq-tablesperf-string-table-concatperf-angle-zeroperf-darkrpvarperf-find-ents-nearperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-config-varperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
21	Codex	gpt-5.6-terra	High	88.9%	94.7%	86.8%	32/2/2/2	15.7s
#21 gpt-5.6-terra High Codex Pass rate88.9% 32 pass · 36 scored Coverage94.7% 36 / 38 evidence-bearing Verified score86.8% 95% interval — · 1 run(s) pass@k88.9% 32/38 fixtures ever solved Outcome mix Pass32 Partial2 Wrong2 Invalid output2 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored36 Passed32 Fixtures solved32/38 Run facts Avg time 15.7s Repeat Single-shot Evidence share 36/38 (94.7%) Verified runs 1 95% interval — Raw label codex/gpt-5.6-terra@high Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 32/38 passed in linked run perf-hook-onceperf-string-table-concatperf-angle-zeroperf-darkrpvarperf-find-ents-nearperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-config-varperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
22	Codex	gpt-5.4-mini	Medium	88.6%	92.1%	85.5%	31/3/1/3	12.8s
#22 gpt-5.4-mini Medium Codex Pass rate88.6% 31 pass · 35 scored Coverage92.1% 35 / 38 evidence-bearing Verified score85.5% 95% interval — · 1 run(s) pass@k88.6% 31/38 fixtures ever solved Outcome mix Pass31 Partial3 Wrong1 Invalid output3 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored35 Passed31 Fixtures solved31/38 Run facts Avg time 12.8s Repeat Single-shot Evidence share 35/38 (92.1%) Verified runs 1 95% interval — Raw label codex/gpt-5.4-mini@medium Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 31/38 passed in linked run perf-find-ents-nearperf-seq-tablesperf-string-table-concatperf-angle-zeroperf-localplayer-cacheperf-looking-atplayer-iteratorents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-ents-iteratorperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-x
23	Codex	gpt-5.4	High	91.2%	89.5%	84.2%	31/2/1/4	12.2s
#23 gpt-5.4 High Codex Pass rate91.2% 31 pass · 34 scored Coverage89.5% 34 / 38 evidence-bearing Verified score84.2% 95% interval — · 1 run(s) pass@k91.2% 31/38 fixtures ever solved Outcome mix Pass31 Partial2 Wrong1 Invalid output4 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored34 Passed31 Fixtures solved31/38 Run facts Avg time 12.2s Repeat Single-shot Evidence share 34/38 (89.5%) Verified runs 1 95% interval — Raw label codex/gpt-5.4@high Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 31/38 passed in linked run perf-ents-iteratorperf-find-ents-nearperf-hook-onceperf-string-table-concatperf-ply-table-indexperf-angle-zeroperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-find-players-nearperf-for-vs-whileperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
24	Codex	gpt-5.4	Extra High	91.2%	89.5%	84.2%	31/2/1/4	20.3s
#24 gpt-5.4 Extra High Codex Pass rate91.2% 31 pass · 34 scored Coverage89.5% 34 / 38 evidence-bearing Verified score84.2% 95% interval — · 1 run(s) pass@k91.2% 31/38 fixtures ever solved Outcome mix Pass31 Partial2 Wrong1 Invalid output4 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored34 Passed31 Fixtures solved31/38 Run facts Avg time 20.3s Repeat Single-shot Evidence share 34/38 (89.5%) Verified runs 1 95% interval — Raw label codex/gpt-5.4@xhigh Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 31/38 passed in linked run perf-ents-iteratorperf-find-ents-nearperf-hook-onceperf-string-table-concatperf-ply-table-indexperf-angle-zeroperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-find-players-nearperf-for-vs-whileperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
25	Codex	gpt-5.6-terra	Low	96.9%	84.2%	82.9%	31/1/0/6	12.9s
#25 gpt-5.6-terra Low Codex Pass rate96.9% 31 pass · 32 scored Coverage84.2% 32 / 38 evidence-bearing Verified score82.9% 95% interval — · 1 run(s) pass@k96.9% 31/38 fixtures ever solved Outcome mix Pass31 Partial1 Wrong0 Invalid output6 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored32 Passed31 Fixtures solved31/38 Run facts Avg time 12.9s Repeat Single-shot Evidence share 32/38 (84.2%) Verified runs 1 95% interval — Raw label codex/gpt-5.6-terra@low Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 31/38 passed in linked run perf-angle-zeroperf-ents-iteratorperf-for-vs-whileperf-localplayer-cacheperf-looking-atperf-string-table-concatperf-find-ents-nearents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-find-players-nearperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
26	Codex	gpt-5.5	High	88.2%	89.5%	81.6%	30/2/2/4	15.4s
#26 gpt-5.5 High Codex Pass rate88.2% 30 pass · 34 scored Coverage89.5% 34 / 38 evidence-bearing Verified score81.6% 95% interval — · 1 run(s) pass@k88.2% 30/38 fixtures ever solved Outcome mix Pass30 Partial2 Wrong2 Invalid output4 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored34 Passed30 Fixtures solved30/38 Run facts Avg time 15.4s Repeat Single-shot Evidence share 34/38 (89.5%) Verified runs 1 95% interval — Raw label codex/gpt-5.5@high Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 30/38 passed in linked run perf-ents-iteratorperf-find-ents-nearperf-hook-onceperf-string-table-concatperf-msg-vs-printperf-table-randomperf-angle-zeroperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-find-players-nearperf-for-vs-whileperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-x-times-xplayer-iterator
27	Codex	gpt-5.4	Low	88.2%	89.5%	80.3%	30/1/3/4	12.0s
#27 gpt-5.4 Low Codex Pass rate88.2% 30 pass · 34 scored Coverage89.5% 34 / 38 evidence-bearing Verified score80.3% 95% interval — · 1 run(s) pass@k88.2% 30/38 fixtures ever solved Outcome mix Pass30 Partial1 Wrong3 Invalid output4 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored34 Passed30 Fixtures solved30/38 Run facts Avg time 12.0s Repeat Single-shot Evidence share 34/38 (89.5%) Verified runs 1 95% interval — Raw label codex/gpt-5.4@low Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 30/38 passed in linked run perf-ents-iteratorperf-find-ents-nearperf-hook-onceperf-string-table-concatperf-angle-zeroperf-darkrpvarperf-ply-table-indexperf-looking-atents-iteratorhook-addisvalidnet-receiversperf-config-varperf-disttosqrperf-find-players-nearperf-for-vs-whileperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-seq-tablesperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-xplayer-iterator
28	Codex	gpt-5.3-codex-spark	Low	81.8%	86.8%	77.6%	27/5/1/5	11.3s
#28 gpt-5.3-codex-spark Low Codex Pass rate81.8% 27 pass · 33 scored Coverage86.8% 33 / 38 evidence-bearing Verified score77.6% 95% interval — · 1 run(s) pass@k81.8% 27/38 fixtures ever solved Outcome mix Pass27 Partial5 Wrong1 Invalid output5 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored33 Passed27 Fixtures solved27/38 Run facts Avg time 11.3s Repeat Single-shot Evidence share 33/38 (86.8%) Verified runs 1 95% interval — Raw label codex/gpt-5.3-codex-spark@low Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 27/38 passed in linked run perf-ents-iteratorperf-find-ents-nearperf-seq-tablesperf-string-table-concatperf-surface-drawrectperf-ply-table-indexperf-angle-zeroperf-for-vs-whileperf-local-colorperf-looking-atplayer-iteratorents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-find-players-nearperf-hook-onceperf-hudpaint-cacheperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-setdrawcolor-splitperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-textperf-table-count-hashperf-table-emptyperf-table-hasvalueperf-table-literalperf-table-randomperf-x-times-x
29	Codex	gpt-5.3-codex-spark	Extra High	87.1%	81.6%	75.0%	27/3/1/7	12.3s
#29 gpt-5.3-codex-spark Extra High Codex Pass rate87.1% 27 pass · 31 scored Coverage81.6% 31 / 38 evidence-bearing Verified score75.0% 95% interval — · 1 run(s) pass@k87.1% 27/38 fixtures ever solved Outcome mix Pass27 Partial3 Wrong1 Invalid output7 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored31 Passed27 Fixtures solved27/38 Run facts Avg time 12.3s Repeat Single-shot Evidence share 31/38 (81.6%) Verified runs 1 95% interval — Raw label codex/gpt-5.3-codex-spark@xhigh Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 27/38 passed in linked run perf-angle-zeroperf-ents-iteratorperf-find-ents-nearperf-seq-tablesperf-setdrawcolor-splitperf-string-table-concatperf-table-hasvalueperf-ply-table-indexperf-find-players-nearperf-looking-atplayer-iteratorents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-msg-vs-printperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-drawrectperf-surface-textperf-table-count-hashperf-table-emptyperf-table-literalperf-table-randomperf-x-times-x
30	Codex	gpt-5.3-codex-spark	High	86.7%	78.9%	72.4%	26/3/1/8	11.2s
#30 gpt-5.3-codex-spark High Codex Pass rate86.7% 26 pass · 30 scored Coverage78.9% 30 / 38 evidence-bearing Verified score72.4% 95% interval — · 1 run(s) pass@k86.7% 26/38 fixtures ever solved Outcome mix Pass26 Partial3 Wrong1 Invalid output8 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored30 Passed26 Fixtures solved26/38 Run facts Avg time 11.2s Repeat Single-shot Evidence share 30/38 (78.9%) Verified runs 1 95% interval — Raw label codex/gpt-5.3-codex-spark@high Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 26/38 passed in linked run perf-ents-iteratorperf-find-ents-nearperf-ply-table-indexperf-seq-tablesperf-setdrawcolor-splitperf-string-table-concatperf-surface-drawrectperf-table-hasvalueperf-msg-vs-printperf-angle-zeroperf-looking-atplayer-iteratorents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-player-cache-hooksperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-textperf-table-count-hashperf-table-emptyperf-table-literalperf-table-randomperf-x-times-x
31	Codex	gpt-5.3-codex-spark	Medium	83.3%	78.9%	68.4%	25/2/3/8	6.0s
#31 gpt-5.3-codex-spark Medium Codex Pass rate83.3% 25 pass · 30 scored Coverage78.9% 30 / 38 evidence-bearing Verified score68.4% 95% interval — · 1 run(s) pass@k83.3% 25/38 fixtures ever solved Outcome mix Pass25 Partial2 Wrong3 Invalid output8 Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel Attempts38 Scored30 Passed25 Fixtures solved25/38 Run facts Avg time 6.0s Repeat Single-shot Evidence share 30/38 (78.9%) Verified runs 1 95% interval — Raw label codex/gpt-5.3-codex-spark@medium Run id ddc5aa24-4d6c-4889-9348-24344c06a4ec Latest run fixtures 25/38 passed in linked run perf-angle-zeroperf-ents-iteratorperf-find-ents-nearperf-seq-tablesperf-setdrawcolor-splitperf-string-table-concatperf-surface-drawrectperf-table-hasvalueperf-msg-vs-printperf-player-cache-hooksperf-ply-table-indexperf-looking-atplayer-iteratorents-iteratorhook-addisvalidnet-receiversperf-config-varperf-darkrpvarperf-disttosqrperf-find-players-nearperf-for-vs-whileperf-hook-onceperf-hudpaint-cacheperf-local-colorperf-local-vs-globalperf-localplayer-cacheperf-meta-vs-argperf-pairs-ipairs-forperf-plain-lua-vs-fnperf-sqlite-vs-mysqlperf-steamid-cacheperf-surface-textperf-table-count-hashperf-table-emptyperf-table-literalperf-table-randomperf-x-times-x

Verified score aggregates compatible runs. Outcomes = pass / partial / wrong / invalid output; harness failures are excluded. Click a row for evidence and the linked run's fixtures.

Fixtures

gmod.ents-iterator.v1
gmod.hook-add.v1
gmod.isvalid.v1
gmod.net-receivers.v1
gmod.perf.angle-zero.v1
gmod.perf.config-var.v1
gmod.perf.darkrpvar.v1
gmod.perf.disttosqr.v1
gmod.perf.ents-iterator.v1
gmod.perf.find-ents-near.v1
gmod.perf.find-players-near.v1
gmod.perf.for-vs-while.v1
gmod.perf.hook-once.v1
gmod.perf.hudpaint-cache.v1
gmod.perf.local-color.v1
gmod.perf.local-vs-global.v1
gmod.perf.localplayer-cache.v1
gmod.perf.looking-at.v1
gmod.perf.meta-vs-arg.v1
gmod.perf.msg-vs-print.v1
gmod.perf.pairs-ipairs-for.v1
gmod.perf.plain-lua-vs-fn.v1
gmod.perf.player-cache-hooks.v1
gmod.perf.ply-table-index.v1
gmod.perf.seq-tables.v1
gmod.perf.setdrawcolor-split.v1
gmod.perf.sqlite-vs-mysql.v1
gmod.perf.steamid-cache.v1
gmod.perf.string-table-concat.v1
gmod.perf.surface-drawrect.v1
gmod.perf.surface-text.v1
gmod.perf.table-count-hash.v1
gmod.perf.table-empty.v1
gmod.perf.table-hasvalue.v1
gmod.perf.table-literal.v1
gmod.perf.table-random.v1
gmod.perf.x-times-x.v1
gmod.player-iterator.v1

Downloads

Results

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel

Run facts

Latest run fixtures

Outcome mix

Attempt funnel