OpenAI
availableShows if the model has enough results for an index.GPT-5.3 Codex
GPT-5.3 Codex is a reasoning model from OpenAI. 19 benchmarks count toward its score, in 6 categories.
IndexOverall score. 50 is the middle.64.8 ±5.2
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.80/s
Input / 1MUS dollars per 1M input tokens.$1.75
Output / 1MUS dollars per 1M output tokens.$14
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
19 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 | 91.5% | 62.3 | — | — | Artificial Analysis |
| LiveCodeBench | Coding | 87.3% | 63.7 | — | 1 Sept 2026 | Vals AI |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 86.0% | 60.5 | — | — | Victor Barres et al. |
| Software Engineering Benchmark Verified | Coding | 85.0% | 65.7 | — | — | Carlos E. Jimenez et al. |
| Artificial Analysis Long Context Reasoning | Reasoning | 83.3% | 65.9 | — | — | Artificial Analysis |
| Artificial Analysis MMMU-Pro | Multimodal | 78.5% | 63.0 | — | — | Artificial Analysis |
| SWE-bench | Coding | 78.0% | 60.1 | — | 1 Sept 2026 | Vals AI |
| Artificial Analysis IFBench | Instruction | 75.4% | 65.6 | — | — | Artificial Analysis |
| SWE-Bench verified | Coding | 74.8% | 57.5 | high effort | — | Epoch AI |
| OSWorld-Verified | Agentic | 64.7% | 53.9 | — | — | Tianbao Xie et al. |
| Terminal-Bench 2.0 | Agentic | 64.0% | 68.4 | — | 4 Jun 2026 | Vals AI |
| Vibe Code Bench v1.1 | Coding | 61.8% | 67.9 | OpenHands | 21 Sept 2026 | Vals AI |
| SWE-Rebench | Coding | 58.2% | — | — | — | Nebius |
| Gert Labs Composite Game Benchmark | Agentic | 57.5% | 63.5 | — | — | Gert Labs |
| SWE-bench Pro | Coding | 56.8% | 58.9 | — | — | Xiang Deng et al. |
| IOI | Coding | 53.8% | 69.1 | — | 21 Sept 2026 | Vals AI |
| Artificial Analysis Omniscience Accuracy | Knowledge | 52.9% | 79.3 | — | — | Artificial Analysis |
| IOI v1 | Coding | 43.8% | 64.9 | — | 9 Aug 2026 | Vals AI |
| Artificial Analysis Humanity's Last Exam | Knowledge | 42.5% | 70.6 | — | — | Artificial Analysis |
| JobBench | Agentic | 33.7% | 57.3 | — | — | Yuetai Li et al. |
| Artificial Analysis Intelligence Index | Knowledge | 32.5% | 63.0 | — | — | Artificial Analysis |
| Critical Physics Tasks | Reasoning | 16.9% | 73.8 | — | — | Artificial Analysis |
19 benchmarks count, from 21 of 22 results. A grey row does not count. Too few models took that benchmark.