OpenAI
availableShows if the model has enough results for an index.GPT-5.1-Codex
GPT-5.1-Codex is a reasoning model from OpenAI. 16 benchmarks count toward its score, in 6 categories.
IndexOverall score. 50 is the middle.54.3 ±5.5
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.39/s
Input / 1MUS dollars per 1M input tokens.$1.25
Output / 1MUS dollars per 1M output tokens.$10
ContextMaximum tokens in one request.400K
EloLMArena rating and rank.N/A
50 is the middle of the board. The range shows the doubt in the index.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
16 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result on the index scale. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| Artificial Analysis GPQA Diamond | Knowledge | 86.0% | 56.7 | — | — | Artificial Analysis |
| LiveCodeBench | Coding | 85.5% | 62.1 | — | 1 Sept 2026 | Vals AI |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 83.0% | 58.4 | — | — | Victor Barres et al. |
| Artificial Analysis MMMU-Pro | Multimodal | 72.5% | 55.7 | — | — | Artificial Analysis |
| Artificial Analysis IFBench | Instruction | 70.0% | 60.1 | — | — | Artificial Analysis |
| Artificial Analysis Long Context Reasoning | Reasoning | 69.3% | 56.2 | — | — | Artificial Analysis |
| SWE-bench Verified | Coding | 66.0% | 50.5 | medium effort · mini-SWE-agent | 1 Sept 2026 | SWE-bench team |
| Terminal-Bench 1.0 | Agentic | 57.5% | 60.3 | — | 12 Jan 2026 | Vals AI |
| Gert Labs Composite Game Benchmark | Agentic | 49.7% | 56.6 | — | — | Gert Labs |
| Artificial Analysis Omniscience Accuracy | Knowledge | 39.9% | 63.2 | — | — | Artificial Analysis |
| JobBench | Agentic | 26.2% | 52.1 | — | — | Yuetai Li et al. |
| Artificial Analysis Humanity's Last Exam | Knowledge | 25.7% | 52.4 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 23.7% | 52.0 | — | — | Artificial Analysis |
| Vibe Code Bench v1.1 | Coding | 13.1% | 47.6 | OpenHands | 21 Sept 2026 | Vals AI |
| Critical Physics Tasks | Reasoning | 5.7% | 50.3 | — | — | Artificial Analysis |
| IOI v1 | Coding | 3.7% | 42.0 | — | 9 Aug 2026 | Vals AI |
16 benchmarks count, from 16 of 16 results. A grey row does not count. Too few models took that benchmark.