gpt-4.1-2025-04-14
5.5%±1.3%
4.2%CI6.9%
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 1 min1 minute ago
All sources syncing normally
- Arena · Text· 1 minute ago
- Arena · WebDev· 1 minute ago
- Arena · Vision· 1 minute ago
- Arena · Agent· 1 minute ago
- GPQA Diamond· 39 minutes ago
- SWE-bench· 39 minutes ago
- Terminal-Bench· 39 minutes ago
- ARC-AGI-2· 39 minutes ago
Filter by org:
Released:
gpt-4.1-mini-2025-04-14
4.5%±1.2%
3.3%CI5.7%
gpt-4.1-nano-2025-04-14
1.0%±0.6%
0.4%CI1.6%
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 46 | gpt-4.1-2025-04-14 | OpenAI | Apr 2025 | $2 / $8 | 5.5% | 4.2%–6.9% | #148–546 | ||
| 49 | gpt-4.1-mini-2025-04-14 | OpenAI | Apr 2025 | $0.40 / $1.60 | 4.5% | 3.3%–5.7% | #130–586 | ||
| 60 | gpt-4.1-nano-2025-04-14 | OpenAI | Apr 2025 | $0.10 / $0.40 | 1.0% | 0.4%–1.6% | #197–987 |
Showing FrontierMath exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.