OpenAIGPT
GPT-4.1
OpenAI · GPT. Released Apr 14, 2025.
GPT-4.1 is a model from OpenAI in the GPT family, released Apr 14, 2025. evals.report tracks 34 reported GPT-4.1 benchmark scores across Berkeley Function Calling Leaderboard, SWE-bench Verified, GPQA Diamond, FrontierMath, AIME (OTIS Mock), LiveCodeBench Pro, WeirdML, Artificial Analysis Intelligence Index, and 26 more — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.
34 results
Benchmark results 34
Compare this model| Benchmark | Category | Score | Metric | Status | Date | |
|---|---|---|---|---|---|---|
| Berkeley Function Calling Leaderboard | Tool use | 53.96% | accuracy | Official | Apr 14, 2025 | Details |
| SWE-bench Verified | Coding | 48.5% | % resolved | Official | Apr 14, 2025 | Details |
| GPQA Diamond | Reasoning | 66.9% | accuracy | Official | Apr 14, 2025 | Details |
| FrontierMath | Reasoning | 5.52% | accuracy | Official | Apr 14, 2025 | Details |
| AIME (OTIS Mock) | Reasoning | 38.3% | accuracy | Official | Apr 14, 2025 | Details |
| LiveCodeBench Pro | Coding | 606 | Codeforces Elo | Official | Apr 14, 2025 | Details |
| WeirdML | Coding | 39.0% | average accuracy | Official | Apr 14, 2025 | Details |
| Artificial Analysis Intelligence Index | Reasoning | 26.3 | Index | Unverified | Apr 14, 2025 | Details |
| Epoch Capabilities Index | Reasoning | 137.6 | Index | Official | Apr 14, 2025 | Details |
| Aider Polyglot | Coding | 52.4% | % correct | Official | Apr 14, 2025 | Details |
| MMLU-Pro | Reasoning | 80.6% | accuracy | Verified | Apr 14, 2025 | Details |
| GAIA: A Benchmark for General AI Assistants | Agents | 50.30% | accuracy | Unverified | Apr 14, 2025 | Details |
| τ²-bench (Telecom) | Tool use | 34% | pass^1 | Verified | Apr 14, 2025 | Details |
| MathVista | Multimodal | 72.2% | accuracy | Verified | Apr 14, 2025 | Details |
| GDPval | Agents | 776 | Elo | Official | Apr 14, 2025 | Details |
| LiveCodeBench | Coding | 45.7% | Pass@1 | Unverified | Apr 14, 2025 | Details |
| SciCode | Coding | 38.1% | accuracy | Unverified | Apr 14, 2025 | Details |
| MMMU (Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark) | Multimodal | 74.8% | accuracy | Unverified | Apr 14, 2025 | Details |
| MultiChallenge | Reasoning | 39.43% | accuracy | Verified | Apr 14, 2025 | Details |
| Arena-Hard-Auto v2.0 | Chat preference | 50.0% | % win rate | Official | Apr 14, 2025 | Details |
| EQ-Bench Creative Writing v3 | Chat preference | 1419 | Elo | Verified | Apr 14, 2025 | Details |
| Design Arena | Chat preference | 1080 | Elo | Verified | Apr 14, 2025 | Details |
| MASK (Model Alignment between Statements and Knowledge) | Other | 51.13 | Honesty score | Verified | Apr 14, 2025 | Details |
| MCP-Universe | Tool use | 19.91% | Overall Success Rate | Verified | Apr 14, 2025 | Details |
| CharXiv | Multimodal | 56.7% | accuracy | Unverified | Apr 14, 2025 | Details |
| FACTS Grounding | Reasoning | 45.6% | Grounding accuracy | Verified | Apr 14, 2025 | Details |
| BigCodeBench | Coding | 33.8% | calibrated Pass@1 | Verified | Apr 14, 2025 | Details |
| SWE-bench Multimodal | Coding | 31.14% | % resolved | Verified | Apr 14, 2025 | Details |
| EnigmaEval | Reasoning | 2.17% | accuracy | Verified | Apr 14, 2025 | Details |
| ZeroBench | Multimodal | 0.0% (pass@1) | accuracy | Verified | Apr 14, 2025 | Details |
| Vectara Hallucination Leaderboard | Other | 5.6% | Hallucination Rate | Official | Apr 14, 2025 | Details |
| PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts | Reasoning | 26.4 | Difficulty-Weighted Accuracy (DW-ACC) | Verified | Apr 14, 2025 | Details |
| Online-Mind2Web | Agents | 36.33% | Task success rate | Verified | Apr 14, 2025 | Details |
| MultiNRC | Reasoning | 21.23% | accuracy | Official | Apr 14, 2025 | Details |