Model
Llama-3.3-70B-Instruct
Meta · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Balrog | 23.0 | average_progress | N/A | Independent | medium | balrogai.com |
| Colombian Legal Reliability Benchmark | 66.2 | accuracy | N/A | Independent | medium | arxiv.org |
| CritPt | 0.0 | accuracy | N/A | Independent | low | epoch.ai |
| GeopoliticalQA | 2.6 | overall | N/A | Independent | medium | arxiv.org |
| GPQA Diamond | 47.4 | accuracy | N/A | Independent | high | epoch.ai |
| LiveBench | 50.2 | global_average | N/A | Independent | medium | livebench.ai |
| MMLU | 86.3 | exact_match | N/A | Independent | medium | arxiv.org |
| PARCEL | 81.0 | accuracy | N/A | Independent | medium | arxiv.org |
| VERITYGATE | 40.1 | claim_survival_rate | veritygate | Independent | medium | arxiv.org |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| SciCode | 26.0 | score | N/A | Independent | medium | artificialanalysis.ai |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| R-GroundBench | 61.1 | accuracy | N/A | Independent | medium | arxiv.org |
Safety & Alignment
Safety & Alignment| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| PFaithBench | 32.6 | overans | N/A | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…