Model
GPT-5.5
OpenAI · closed weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CL-bench Life | 22.2 | overall | N/A | Independent | low | epoch.ai |
| CritPt | 27.1 | accuracy | N/A | Independent | low | epoch.ai |
| GPQA Diamond | 90.7 | accuracy | N/A | Independent | high | epoch.ai |
| SimpleQA Verified | 63.0 | accuracy | N/A | Independent | high | epoch.ai |
| TasteVal | 0.5 | compute_multiplier | N/A | Independent | medium | arxiv.org |
Math
Math| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| EfficientOpt | 72.1 | solver_time_ratio | N/A | Independent | medium | arxiv.org |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| A2Z GameSpec-Bench | 63.2 | gdd_fidelity | N/A | Independent | medium | arxiv.org |
| AgentSWE | 5.8 | score | N/A | Independent | medium | arxiv.org |
| CRBugBench | 43.7 | success_rate | N/A | Independent | medium | arxiv.org |
| DeepSWE | 67.0 | pass@1 | mini-swe-agent | Independent | medium | deepswe.datacurve.ai |
| GSO | 40.2 | score_opt@1 | OpenHands | Independent | medium | gso-bench.github.io |
| PLCWorld | 37.9 | success_rate | N/A | Independent | medium | arxiv.org |
| SciCode | 56.1 | score | N/A | Independent | medium | artificialanalysis.ai |
| SimuVerity | 41.7 | score | codex | Independent | medium | arxiv.org |
| SWE-Duel | 2.8 | bradley_terry_log_strength | codex | Independent | medium | arxiv.org |
| SWE-Duel | 2.1 | bradley_terry_log_strength | mini-swe-agent | Independent | medium | arxiv.org |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| AgentHorizon | 80.9 | accuracy | codex | Independent | medium | arxiv.org |
| APTInvestBench | 60.7 | coverage_rate | N/A | Independent | medium | arxiv.org |
| DeepResearch Bench | 54.0 | average_score | N/A | Independent | medium | evals.futuresearch.ai |
| ExploitBench | 47.4 | mean_capability | N/A | Independent | low | epoch.ai |
| ExploitBench | 41.6 | mean_capability | Codex | Independent | low | epoch.ai |
| KlinikeBench | 16.8 | strict_pass@1 | N/A | Independent | medium | arxiv.org |
| Legal Research Bench | 40.0 | accuracy | N/A | Independent | medium | arxiv.org |
| MisVisAgentBench | 34.3 | pra | N/A | Independent | medium | arxiv.org |
| Open-Endedness Bench | 1.0 | e4_no_reward_hacking | N/A | Independent | medium | arxiv.org |
| OpenGameEval | 46.1 | pass_rate | N/A | Independent | medium | arxiv.org |
| ReFract | 0.6 | success_rate | function calling | Independent | medium | arxiv.org |
| Synthetic Trading Benchmark | 9.0 | e0_sharpe | N/A | Independent | medium | arxiv.org |
| Terminal-Bench | 84.7 | accuracy | NexAU-AHE | Independent | medium | tbench.ai |
| Terminal-Bench | 83.1 | accuracy | Capy | Independent | medium | tbench.ai |
| Terminal-Bench | 82.2 | accuracy | Codex CLI | Independent | medium | tbench.ai |
| Terminal-Bench | 82.0 | accuracy | Codex | Independent | medium | tbench.ai |
| Terminal-Bench | 66.1 | accuracy | clnkr | Independent | medium | tbench.ai |
| XiangqiBench | 17.6 | pass@3 | N/A | Independent | medium | arxiv.org |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ChartBmkAgent | 82.7 | accuracy | N/A | Independent | medium | arxiv.org |
| EditJudgeBias | 8.2 | rubric_ratings_(1-10)_and_pairwise_preferences | N/A | Independent | medium | arxiv.org |
| Front2Back-ReID | 62.8 | accuracy | N/A | Independent | medium | arxiv.org |
| GDP.pdf | 26.0 | gdp.pdf_score | N/A | Independent | medium | surgehq.ai |
| MiniVer-V | 0.6 | f1 | N/A | Independent | medium | arxiv.org |
| MM-FinEval | 1.0 | fut_3d_da_↑_↑ | N/A | Independent | medium | arxiv.org |
| MM-FinEval | 1.0 | fut_7d_da_↑_↑ | N/A | Independent | medium | arxiv.org |
| MM-FinEval | 0.5 | da_↑_↑ | N/A | Independent | medium | arxiv.org |
| R-GroundBench | 73.5 | accuracy | N/A | Independent | medium | arxiv.org |
Instruction Following
Instruction Following| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| UXBench Pro | -0.1 | turn_bt | N/A | Independent | medium | arxiv.org |
| WISE | 62.7 | compliance | N/A | Independent | medium | arxiv.org |
Safety & Alignment
Safety & Alignment| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Mental Health Stigma Benchmark | 0.5 | f1 | N/A | Independent | medium | arxiv.org |
| RobustReview | 0.6 | joint_stability-discrimination_profile_and_human_alignment_scores | N/A | Independent | medium | arxiv.org |
| SWE-DeceptionBench | 2.5 | active_deception_rate | N/A | Independent | medium | arxiv.org |
Abstract Reasoning
Abstract ReasoningReproduced by the community
Loading community runs…