Model
GPT-4.1
OpenAI · closed weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Contradiction Benchmark for Review Evaluation | 100.0 | accuracy | N/A | Independent | medium | arxiv.org |
| EnigmaEval | 2.2 | accuracy | N/A | Independent | medium | labs.scale.com |
| GPQA Diamond | 66.9 | accuracy | N/A | Independent | high | epoch.ai |
| HLE | 5.4 | accuracy | N/A | Independent | low | epoch.ai |
| ScholarCatalyst | 0.4 | r@20 | tool-calling agent | Independent | medium | arxiv.org |
| SimpleQA Verified | 31.1 | accuracy | N/A | Independent | high | epoch.ai |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Aider Polyglot | 52.4 | percent_correct | N/A | Independent | medium | aider.chat |
| SWE-bench Verified | 48.5 | resolved_rate | N/A | Independent | high | epoch.ai |
| Web-Bench | 21.1 | pass@1 | N/A | Independent | medium | arxiv.org |
| WebUIProof | 41.4 | success_rate | N/A | Independent | medium | arxiv.org |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| EnterpriseBench | 8.3 | beergame_cost_x10^4_(lower_is_better) | gepa | Independent | medium | arxiv.org |
| EnterpriseBench | 8.3 | beergame_cost_x10^4_(lower_is_better) | gepa+ace | Independent | medium | arxiv.org |
| EnterpriseBench | 8.1 | beergame_cost_x10^4_(lower_is_better) | dc | Independent | medium | arxiv.org |
| EnterpriseBench | 7.7 | beergame_cost_x10^4_(lower_is_better) | amem | Independent | medium | arxiv.org |
| EnterpriseBench | 7.2 | beergame_cost_x10^4_(lower_is_better) | single-agent | Independent | medium | arxiv.org |
| EnterpriseBench | 6.8 | beergame_cost_x10^4_(lower_is_better) | debate | Independent | medium | arxiv.org |
| EnterpriseBench | 6.7 | beergame_cost_x10^4_(lower_is_better) | discussion | Independent | medium | arxiv.org |
| EnterpriseBench | 6.6 | beergame_cost_x10^4_(lower_is_better) | reflexion | Independent | medium | arxiv.org |
| EnterpriseBench | 6.5 | beergame_cost_x10^4_(lower_is_better) | self-refine | Independent | medium | arxiv.org |
| FinSkillBench | 0.5 | score | N/A | Independent | medium | arxiv.org |
| KlinikeBench | 7.5 | strict_pass@1 | N/A | Independent | medium | arxiv.org |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| GeoBench | 72.0 | acw_country_% | N/A | Independent | medium | geobench.org |
| ImplicitQA | 54.3 | average_accuracy | N/A | Independent | medium | paperswithcode.com |
| R-GroundBench | 70.8 | accuracy | N/A | Independent | medium | arxiv.org |
Abstract Reasoning
Abstract ReasoningMultilingual
Multilingual| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Cross-Lingual Unlearning Tensor | 88.3 | residual_access | N/A | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…