GPT-5 Medium (August 2025)
69.1%
no interval published
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 28 min28 minutes ago
All sources syncing normally
- Arena · Text· 1 hour ago
- Arena · WebDev· 1 hour ago
- Arena · Vision· 1 hour ago
- Arena · Agent· 1 hour ago
- GPQA Diamond· 28 minutes ago
- SWE-bench· 28 minutes ago
- Terminal-Bench· 28 minutes ago
- ARC-AGI-2· 28 minutes ago
Filter by org:
Released:
o4-mini High (April 2025)
64.8%
no interval published
Claude Opus 4.1 High (August 2025)
51.5%
no interval published
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 | ± CI | Swing | Add to compare | |||||
|---|---|---|---|---|---|---|---|---|---|
| 1 | GPT-5 Medium (August 2025) | openai | — | — | 69.1% | — | — | ||
| 2 | o4-mini High (April 2025) | openai | — | — | 64.8% | — | — | ||
| 3 | Claude Opus 4.1 High (August 2025) | anthropic | — | — | 51.5% | — | — | ||
| 4 | o3 Medium (April 2025) | openai | — | — | 46.3% | — | — | ||
| 5 | GPT-4.1 (April 2025) | openai | Apr 2025 | $2 / $8 | 45.0% | — | #148–546 | ||
| 6 | DeepSeek V3 (March 2025) | deepseek | Dec 2024 | — | 39.1% | — | #178–644 | ||
| 7 | DeepSeek R1 (January 2025) | deepseek | Jan 2025 | $0.70 / $2.50 | 38.1% | — | #117–389 | ||
| 8 | Claude-3.7 Sonnet (February 2025) | anthropic | Feb 2025 | — | 29.3% | — | #128–354 | ||
| 9 | Gemini 2.0 Flash (February 2025) | — | — | 27.0% | — | — |
Showing USACO (HAL) exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.