Model
GPT-5.2-chat
OpenAI · closed weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CL-bench | 18.2 | overall | N/A | Independent | low | epoch.ai |
| Contradiction Benchmark for Review Evaluation | 96.3 | accuracy | N/A | Independent | medium | arxiv.org |
| EnigmaEval | 10.4 | accuracy | N/A | Independent | medium | labs.scale.com |
| GDPval | 49.7 | win_rate | N/A | Independent | low | epoch.ai |
| GPQA Diamond | 91.4 | accuracy | N/A | Independent | high | epoch.ai |
| HLE | 27.8 | accuracy | N/A | Independent | low | epoch.ai |
| PHRBench | 91.0 | auroc | N/A | Independent | medium | arxiv.org |
| SimpleQA Verified | 37.1 | accuracy | N/A | Independent | high | epoch.ai |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| GSO | 27.4 | score_opt@1 | OpenHands | Independent | medium | gso-bench.github.io |
| SWE-bench Verified | 73.8 | resolved_rate | N/A | Independent | high | epoch.ai |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| DeepResearch Bench | 41.1 | average_score | N/A | Independent | medium | evals.futuresearch.ai |
| Terminal-Bench | 64.9 | accuracy | Droid | Independent | medium | tbench.ai |
| Terminal-Bench | 62.9 | accuracy | Codex CLI | Independent | medium | tbench.ai |
| Terminal-Bench | 60.7 | accuracy | Mux | Independent | medium | tbench.ai |
| Terminal-Bench | 54.0 | accuracy | Terminus 2 | Independent | medium | tbench.ai |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CogEmo-Bench | 36.9 | m-f1 | N/A | Independent | medium | arxiv.org |
| EgoExo-Next | 43.2 | accuracy | N/A | Independent | medium | arxiv.org |
| FigCodeBench | 76.3 | mmos | N/A | Independent | medium | arxiv.org |
| SQUARE-Bench | 87.1 | overall | N/A | Independent | medium | arxiv.org |
| WOVEN | 70.7 | accuracy | N/A | Independent | medium | arxiv.org |
Abstract Reasoning
Abstract ReasoningMultilingual
Multilingual| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Cross-Lingual Unlearning Tensor | 94.8 | residual_access | N/A | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…