OpenAIo-series
o4-mini
OpenAI · o-series. Released Apr 16, 2025.
o4-mini is a model from OpenAI in the o-series family, released Apr 16, 2025. evals.report tracks 38 reported o4-mini benchmark scores across FrontierMath, Berkeley Function Calling Leaderboard, ARC-AGI-1, ARC-AGI-2, LiveCodeBench Pro, GPQA Diamond, AIME (OTIS Mock), SimpleQA Verified, and 30 more — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.
38 results
Benchmark results 38
Compare this model| Benchmark | Category | Score | Metric | Status | Date | |
|---|---|---|---|---|---|---|
| FrontierMath | Reasoning | 24.83% | accuracy | Official | Apr 16, 2025 | Details |
| Berkeley Function Calling Leaderboard | Tool use | 53.24% | accuracy | Official | Apr 16, 2025 | Details |
| ARC-AGI-1 | Reasoning | 58.67% | accuracy | Official | Apr 16, 2025 | Details |
| ARC-AGI-2 | Reasoning | 6.11% | accuracy | Official | Apr 16, 2025 | Details |
| LiveCodeBench Pro | Coding | 2092 | Codeforces Elo | Official | Apr 16, 2025 | Details |
| GPQA Diamond | Reasoning | 79.6% | accuracy | Official | Apr 16, 2025 | Details |
| AIME (OTIS Mock) | Reasoning | 81.7% | accuracy | Official | Apr 16, 2025 | Details |
| SimpleQA Verified | Other | 23.9% | accuracy | Official | Apr 16, 2025 | Details |
| WeirdML | Coding | 52.6% | average accuracy | Official | Apr 16, 2025 | Details |
| Epoch Capabilities Index | Reasoning | 146.9 | Index | Official | Apr 16, 2025 | Details |
| Aider Polyglot | Coding | 72.0% | % correct | Official | Apr 16, 2025 | Details |
| MMLU-Pro | Reasoning | 83.2% | accuracy | Verified | Apr 16, 2025 | Details |
| GAIA: A Benchmark for General AI Assistants | Agents | 36.8% | accuracy | Unverified | Apr 16, 2025 | Details |
| BrowseComp | Agents | 28.3% | accuracy | Verified | Apr 16, 2025 | Details |
| τ²-bench (Telecom) | Tool use | 42% | pass^1 | Verified | Apr 16, 2025 | Details |
| MathVista | Multimodal | 84.3% | accuracy | Verified | Apr 16, 2025 | Details |
| GDPval | Agents | 1008 | Elo | Official | Apr 16, 2025 | Details |
| LiveCodeBench | Coding | 85.9% | Pass@1 | Unverified | Apr 16, 2025 | Details |
| SciCode | Coding | 46.5% | accuracy | Unverified | Apr 16, 2025 | Details |
| MMMU (Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark) | Multimodal | 81.6% | accuracy | Verified | Apr 16, 2025 | Details |
| MultiChallenge | Reasoning | 44.90% | accuracy | Verified | Apr 16, 2025 | Details |
| Arena-Hard-Auto v2.0 | Chat preference | 74.6% | % win rate | Official | Apr 16, 2025 | Details |
| Design Arena | Chat preference | 1030 | Elo | Verified | Apr 16, 2025 | Details |
| MASK (Model Alignment between Statements and Knowledge) | Other | 78.60 | Honesty score | Verified | Apr 16, 2025 | Details |
| MCP-Universe | Tool use | 25.97% | Overall Success Rate | Verified | Apr 16, 2025 | Details |
| CharXiv | Multimodal | 72.0% | accuracy | Unverified | Apr 16, 2025 | Details |
| FACTS Grounding | Reasoning | 29.3% | Grounding accuracy | Verified | Apr 16, 2025 | Details |
| SWE-bench Multimodal | Coding | 33.85% | % resolved | Verified | Apr 16, 2025 | Details |
| EnigmaEval | Reasoning | 9.21% | accuracy | Verified | Apr 16, 2025 | Details |
| ZeroBench | Multimodal | 2.0% (pass@1) | accuracy | Verified | Apr 16, 2025 | Details |
| IMO-Bench | Reasoning | 67.9% | accuracy | Verified | Apr 16, 2025 | Details |
| PutnamBench | Reasoning | 2 | Problems solved | Verified | Apr 16, 2025 | Details |
| FrontierMath Tier 4 | Reasoning | 6.3% | accuracy | Official | Apr 16, 2025 | Details |
| Vectara Hallucination Leaderboard | Other | 18.6% | Hallucination Rate | Official | Apr 16, 2025 | Details |
| PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts | Reasoning | 45.6 | Difficulty-Weighted Accuracy (DW-ACC) | Verified | Apr 16, 2025 | Details |
| Online-Mind2Web | Agents | 32.00% | Task success rate | Verified | Apr 16, 2025 | Details |
| GSO: Software Optimization Benchmark for SWE-Agents | Coding | 3.6% | Opt@1 | Official | Apr 16, 2025 | Details |
| MultiNRC | Reasoning | 22.18% | accuracy | Official | Apr 16, 2025 | Details |