chatgpt-4o-latest-20250326
59±1
57interval61
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,308
- Last sync
- 39 min39 minutes ago
All sources syncing normally
- Arena · Text· 39 minutes ago
- Arena · WebDev· 39 minutes ago
- Arena · Vision· 39 minutes ago
- Arena · Agent· 39 minutes ago
- GPQA Diamond· 1 hour ago
- SWE-bench· 1 hour ago
- Terminal-Bench· 1 hour ago
- ARC-AGI-2· 1 hour ago
Filter by org:
Released:
chatgpt-4o-latest-0903
50±0
50interval51
gpt-4.5-preview-2025-02-27
47±2
44interval48
One grid, every column. Pick axes in the Axes panel — one axis ranks like a single board, several blend into a weighted composite, all of them read as the index. Rank is assigned before any filter and never renumbers.
| Model | Org | Interval | Swing | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | Add to compare | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 175 | chatgpt-4o-latest-20250326 | openai | Aug 2024 | — | 59.0 65.7Ranked 59.0 = (4 × 65.7 + 3 × 50) ÷ 7. 65.7 is the mean percentile over the 4 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 57–61 | 24 | 4/22 | #79–175 | 80 | — | 62 | 56 | — | — | — | — | — | — | — | — | — | — | 66 | — | — | — | — | — | — | — | ||
| 402 | chatgpt-4o-latest-0903 | OpenAI | — | — | 50.4 51.5Ranked 50.4 = (1 × 51.5 + 3 × 50) ÷ 4. 51.5 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | — | — | 1/22low | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 52 | — | — | — | — | — | — | — | ||
| 530 | gpt-4.5-preview-2025-02-27 | openai | Feb 2025 | — | 46.5 45.2Ranked 46.5 = (8 × 45.2 + 3 × 50) ÷ 11. 45.2 is the mean percentile over the 8 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 44–48 | 65 | 8/22 | #74–530 | 81 | — | 56 | — | — | — | — | 50 | 35 | — | — | 16 | 17 | 28 | 79 | — | — | — | — | — | — | — | ||
| 546 | gpt-4.1-2025-04-14 | openai | Apr 2025 | $2 / $8 | 46.0 45.3Ranked 46.0 = (16 × 45.3 + 3 × 50) ÷ 19. 45.3 is the mean percentile over the 16 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 44–48 | 67 | 16/22 | #148–546 | 67 | — | 51 | 21 | — | — | — | 48 | 36 | 35 | 27 | 13 | 15 | 18 | 60 | 80 | — | — | 70 | 53 | 48 | 81 | ||
| 586 | gpt-4.1-mini-2025-04-14 | openai | Apr 2025 | $0.40 / $1.60 | 44.7 43.4Ranked 44.7 = (12 × 43.4 + 3 × 50) ÷ 15. 43.4 is the mean percentile over the 12 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 43–46 | 65 | 12/22 | #130–586 | 57 | — | 48 | — | — | — | — | 48 | 37 | 32 | 9 | 11 | — | — | 55 | 73 | — | — | 60 | 56 | 36 | — | ||
| 697 | gpt-4-0125-preview | openai | Jan 2024 | — | 42.1 34.2Ranked 42.1 = (3 × 34.2 + 3 × 50) ÷ 6. 34.2 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 41–43 | 18 | 3/22 | #252–697 | 37 | — | — | — | — | — | — | 24 | — | — | — | — | — | — | 42 | — | — | — | — | — | — | — | ||
| 817 | GPT-4 | openai | Mar 2023 | $30 / $60 | 39.2 22.9Ranked 39.2 = (2 × 22.9 + 3 × 50) ÷ 5. 22.9 is the mean percentile over the 2 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | — | 2 | 2/22low | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 22 | — | 24 | — | ||
| 837 | api-gpt-4o-search | openai | Oct 2026 | — | 38.7 4.8Ranked 38.7 = (1 × 4.8 + 3 × 50) ÷ 4. 4.8 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 38–39 | — | 1/22low | — | — | — | — | — | 5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | ||
| 874 | gpt-4-1106-preview | openai | Nov 2023 | — | 38.0 29.0Ranked 38.0 = (4 × 29.0 + 3 × 50) ÷ 7. 29.0 is the mean percentile over the 4 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 37–39 | 34 | 4/22 | #248–874 | 36 | — | — | — | — | — | — | 24 | — | — | — | — | — | — | 44 | — | 11 | — | — | — | — | — | ||
| 922 | gpt-4-turbo-2024-04-09 | openai | Apr 2024 | $10 / $30 | 36.5 31.5Ranked 36.5 = (8 × 31.5 + 3 × 50) ÷ 11. 31.5 is the mean percentile over the 8 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 35–38 | 32 | 8/22 | #227–922 | 41 | — | 21 | — | — | — | — | 29 | 20 | — | — | — | — | 16 | 48 | — | — | — | 39 | 37 | — | — | ||
| 959 | gpt-4o-2024-05-13 | openai | May 2024 | $2.50 / $10 | 33.9 30.6Ranked 33.9 = (15 × 30.6 + 3 × 50) ÷ 18. 30.6 is the mean percentile over the 15 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 32–35 | 66 | 15/22 | #154–959 | 48 | — | 37 | — | — | — | — | 34 | 19 | 7 | 22 | 11 | 2 | 3 | 56 | — | 22 | — | 68 | 52 | 30 | 49 | ||
| 964 | gpt-4-0314 | openai | Mar 2023 | — | 33.4 16.8Ranked 33.4 = (3 × 16.8 + 3 × 50) ÷ 6. 16.8 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 32–35 | 28 | 3/22 | #260–964 | 31 | — | — | — | — | — | — | 17 | 3 | — | — | — | — | — | — | — | — | — | — | — | — | — | ||
| 976 | gpt-4-0613 | openai | Jun 2023 | — | 32.6 19.6Ranked 32.6 = (4 × 19.6 + 3 × 50) ÷ 7. 19.6 is the mean percentile over the 4 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 31–34 | 28 | 4/22 | #270–976 | 28 | — | — | — | — | — | — | 11 | 6 | — | — | — | — | — | 34 | — | — | — | — | — | — | — | ||
| 987 | gpt-4.1-nano-2025-04-14 | openai | Apr 2025 | $0.10 / $0.40 | 31.6 27.0Ranked 31.6 = (12 × 27.0 + 3 × 50) ÷ 15. 27.0 is the mean percentile over the 12 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 30–33 | 49 | 12/22 | #197–987 | 40 | — | 19 | — | — | — | — | 33 | 32 | 14 | 1 | 11 | — | — | 26 | 50 | — | — | 32 | 43 | 22 | — | ||
| 1023 | gpt-4o-mini-2024-07-18 | openai | Jul 2024 | $0.15 / $0.60 | 26.7 20.3Ranked 26.7 = (11 × 20.3 + 3 × 50) ÷ 14. 20.3 is the mean percentile over the 11 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 25–28 | 37 | 11/22 | #236–1023 | 38 | — | 21 | — | — | — | — | 19 | 21 | — | 2 | 11 | — | 1 | 33 | — | — | — | 31 | 29 | 18 | — |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model