Model
GPT-4o-mini
OpenAI · closed weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Balrog | 17.4 | average_progress | N/A | Independent | medium | balrogai.com |
| BoolQ | 88.7 | score | N/A | Independent | medium | arxiv.org |
| GPQA Diamond | 37.7 | accuracy | N/A | Independent | high | epoch.ai |
| LiveBench | 41.3 | global_average | N/A | Independent | medium | livebench.ai |
| MMLU | 81.8 | exact_match | N/A | Independent | medium | arxiv.org |
| MS-Exam-Gen | 80.6 | accuracy | N/A | Independent | medium | arxiv.org |
| PHRBench | 89.3 | auroc | N/A | Independent | medium | arxiv.org |
| PhysicsMate | 69.5 | accuracy | llm-judge (gemini-2.5-flash-lite) | Independent | medium | arxiv.org |
| PIQA | 88.7 | score | N/A | Independent | medium | arxiv.org |
| SimpleQA Verified | 8.3 | accuracy | N/A | Independent | high | epoch.ai |
| VERITYGATE | 19.7 | claim_survival_rate | veritygate | Independent | medium | arxiv.org |
Math
MathCoding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Abt-Buy | 87.7 | f1_(%) | N/A | Independent | medium | arxiv.org |
| Aider Polyglot | 3.6 | percent_correct | N/A | Independent | medium | aider.chat |
| AlgoREval | 66.3 | accuracy | N/A | Independent | medium | arxiv.org |
| Amazon-Google | 59.2 | f1_(%) | N/A | Independent | medium | arxiv.org |
| Web-Bench | 8.5 | pass@1 | N/A | Independent | medium | arxiv.org |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| DyadMem | 47.9 | accuracy | N/A | Independent | medium | arxiv.org |
| KlinikeBench | 0.6 | strict_pass@1 | N/A | Independent | medium | arxiv.org |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| GeoBench | 64.0 | acw_country_% | N/A | Independent | medium | geobench.org |
| MM-Vet | 68.6 | gpt-4_score | N/A | Independent | medium | arxiv.org |
| MM-Vet v2 | 66.8 | gpt-4_score | N/A | Independent | medium | arxiv.org |
| Video-MME | 68.9 | accuracy_(%) | N/A | Independent | medium | arxiv.org |
| Video-MME | 64.8 | overall_(no_subtitles) | N/A | Independent | medium | video-mme.github.io |
Instruction Following
Instruction FollowingSafety & Alignment
Safety & AlignmentAbstract Reasoning
Abstract ReasoningReproduced by the community
Loading community runs…