Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works
How smart is GPT-5 mini?
GPT-5 mini is a model from OpenAI, released on Aug 7, 2025. Its SI-IQ is 115 (90% interval 112–118), estimated from 11 benchmark results by 3 independent evaluators. Its strongest area is Math and its weakest is Knowledge.
Facts
- Developer
- OpenAI
- Released
- Aug 7, 2025
- Access
- API access
- Benchmarks used
- 11 results from 3 evaluators
- API price
- $0.25 input / $2.00 output per 1M tokens (developer's price list, Oct 18, 2026)
- Context window
- 272,000 tokens
Ability by area (SI-IQ, 90% interval)
Every benchmark result we used
Each score is one value exactly as the source published it: for Epoch AI the best of its run settings, for OpenRouter the median hosting provider (the developer's own hosting when it ran the test). “Implied SI-IQ” is the ability that this single result points to; the overall SI-IQ is their precision-weighted average.
| Benchmark | Score | Evaluated by | Source |
|---|---|---|---|
| Chess Puzzles | 24.0% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| Mystery Game Puzzles | 10.0% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| FrontierMath Tier 4 | 12.2% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| FrontierMath Tiers 1–3 | 46.7% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| MATH Level 5 | 97.8% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| OTIS Mock AIME 2024–2025 | 86.7% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| SWE-bench Verified (Epoch AI run) | 64.7% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| GPQA Diamond | 75.0% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| GPQA Diamond (OpenRouter run) | 80.1% | OpenRouter | OpenRouter benchmark datasets · data file |
| SimpleQA Verified | 21.6% | Epoch AI | Epoch AI Benchmarking Hub · data file |
| Berkeley Function Calling Leaderboard | 55.5% | UC Berkeley (Gorilla) | Berkeley Function Calling Leaderboard · data file |
| τ²-bench Airline (OpenRouter run) | 71.2% | OpenRouter | OpenRouter benchmark datasets · data file |
Models with similar SI-IQ
| Model | SI-IQ | |
|---|---|---|
| Qwen3.6 27BAlibaba | 115 | GPT-5 mini vs Qwen3.6 27B |
| Qwen3.7-PlusAlibaba | 115 | GPT-5 mini vs Qwen3.7-Plus |
| Claude Opus 4.5Anthropic | 115 | GPT-5 mini vs Claude Opus 4.5 |
| GLM-5.1Z.ai (Zhipu AI) | 116 | GPT-5 mini vs GLM-5.1 |
| o3OpenAI | 116 | GPT-5 mini vs o3 |
Computed with SI-IQ method version 1.0.0. Read the full methodology
Data sources: Berkeley Function Calling Leaderboard, Gorilla project (Apache-2.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); API list prices via LiteLLM's price table (MIT); each price links to the developer's pricing page; Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..