Model
GPT-5-mini
OpenAI · closed weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CritPt | 0.0 | accuracy | N/A | Independent | low | epoch.ai |
| EnigmaEval | 8.2 | accuracy | N/A | Independent | medium | labs.scale.com |
| GPQA Diamond | 75.0 | accuracy | N/A | Independent | high | epoch.ai |
| HLE | 19.4 | accuracy | N/A | Independent | low | epoch.ai |
| SimpleQA Verified | 21.6 | accuracy | N/A | Independent | high | epoch.ai |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| SciCode | 39.2 | score | N/A | Independent | medium | artificialanalysis.ai |
| SWE-bench Verified | 64.7 | resolved_rate | N/A | Independent | high | epoch.ai |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Terminal-Bench | 34.8 | accuracy | spoox-o-m | Independent | medium | tbench.ai |
| Terminal-Bench | 34.8 | accuracy | spoox-m | Independent | low | epoch.ai |
| Terminal-Bench | 31.9 | accuracy | Codex CLI | Independent | medium | tbench.ai |
| Terminal-Bench | 29.2 | accuracy | OpenHands | Independent | medium | tbench.ai |
| Terminal-Bench | 24.0 | accuracy | Terminus 2 | Independent | medium | tbench.ai |
| Terminal-Bench | 22.2 | accuracy | Mini-SWE-Agent | Independent | medium | tbench.ai |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| BrainTRACE | 38.2 | accuracy | N/A | Independent | medium | arxiv.org |
| VisualNoiseQA | 47.0 | accuracy | bp | Independent | medium | arxiv.org |
Safety & Alignment
Safety & AlignmentAbstract Reasoning
Abstract ReasoningMultilingual
Multilingual| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Cross-Lingual Unlearning Tensor | 87.2 | residual_access | N/A | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…