OpenAI
availableShows if the model has enough results for an index.GPT-4o
GPT-4o is a non-reasoning model from OpenAI. 24 benchmarks count toward its score, in 7 categories.
IndexOverall score. 50 is the middle.27.6 ±3.8
CoverageShare of the index weight with results.95%
SpeedOutput tokens per second.60/s
Input / 1MUS dollars per 1M input tokens.$2.5 batch $1.25
Output / 1MUS dollars per 1M output tokens.$10 batch $5 US dollars per 1M output tokens in a batch.
ContextMaximum tokens in one request.128K
EloLMArena rating and rank.1282 (#254)
50 is the middle of the board. The range shows the doubt in the index. Batch work costs less.
45,499 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
24 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. |
|---|---|---|---|---|---|---|
| MGSM | Multilingual | 90.5% | — | — | 9 Jan 2026 | Vals AI |
| MATH 500 | Math | 74.6% | 25.2 | — | 9 Jan 2026 | Vals AI |
| MMLU Pro | Knowledge | 73.3% | 36.0 | — | 1 Sept 2026 | Vals AI |
| MMMU Pro | Multimodal | 63.1% | 30.0 | — | 1 Sept 2026 | Vals AI |
| Artificial Analysis GPQA Diamond | Knowledge | 54.3% | 24.2 | — | — | Artificial Analysis |
| GPQA Diamond | Knowledge | 52.0% | 26.3 | — | 1 Sept 2026 | Vals AI |
| MATH level 5 | Math | 51.0% | 23.7 | — | — | Epoch AI |
| Artificial Analysis Long Context Reasoning | Reasoning | 49.3% | 42.4 | — | — | Artificial Analysis |
| GPQA diamond | Knowledge | 48.9% | 23.4 | — | — | Epoch AI |
| LiveCodeBench | Coding | 43.4% | 23.8 | — | 1 Sept 2026 | Vals AI |
| Artificial Analysis IFBench | Instruction | 34.3% | 23.9 | — | — | Artificial Analysis |
| SWE-Bench verified | Coding | 31.0% | 22.4 | — | — | Epoch AI |
| SWE-bench Lite | Coding | 27.8% | 27.0 | SIMA | 11 Sept 2025 | SWE-bench team |
| SWE-bench Verified | Coding | 26.6% | 18.8 | AppMap Navie | 1 Sept 2026 | SWE-bench team |
| SimpleQA Verified | Knowledge | 26.0% | 45.6 | — | — | Epoch AI |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 25.1% | 16.8 | — | — | Victor Barres et al. |
| SWE-bench Verified | Coding | 23.2% | 16.1 | SWE-agent | 26 Feb 2026 | SWE-bench team |
| SWE-bench Lite | Coding | 21.7% | 21.7 | AppMap Navie | 11 Sept 2025 | SWE-bench team |
| Artificial Analysis Omniscience Accuracy | Knowledge | 19.9% | 38.5 | — | — | Artificial Analysis |
| SWE-bench (full test split) | Coding | 14.6% | — | AppMap Navie | 19 Dec 2025 | SWE-bench team |
| Chess Puzzles | Reasoning | 13.0% | 40.3 | — | — | Epoch AI |
| AIME | Math | 12.9% | 19.7 | — | 16 Apr 2026 | Vals AI |
| SWE-bench Multimodal | Multimodal | 10.6% | — | SWE-agent | 17 Nov 2025 | SWE-bench team |
| Artificial Analysis Intelligence Index | Knowledge | 8.4% | 32.9 | — | — | Artificial Analysis |
| OTIS Mock AIME 2024-2025 | Math | 6.3% | 15.1 | — | — | Epoch AI |
| SWE-bench Multimodal | Multimodal | 6.0% | — | RAG | 17 Nov 2025 | SWE-bench team |
| ARC-AGI-1 (semi-private) | Reasoning | 4.5% | 29.3 | — | — | ARC Prize Foundation |
| Artificial Analysis Humanity's Last Exam | Knowledge | 2.4% | 27.2 | — | — | Artificial Analysis |
| FrontierMath-Tiers-1-3-v2-Private | Math | 0.4% | 31.6 | — | — | Epoch AI |
| FrontierMath-2025-02-28-Private | Math | 0.3% | 31.0 | — | — | Epoch AI |
| Critical Physics Tasks | Reasoning | 0.0% | 38.4 | — | — | Artificial Analysis |
| ARC-AGI-2 (semi-private) | Reasoning | 0.0% | 39.7 | — | — | ARC Prize Foundation |
24 benchmarks count, from 28 of 32 results. A grey row does not count. Too few models took that benchmark.