Benchmarks
General benchmarks
This topic groups benchmarks that cover several kinds of task.
We track 105 benchmarks in this topic. Main benchmarks are listed by how many models they cover, most first. Where a benchmark has separate results for a subset of its tasks, those results appear right under it. Click one for its leaderboard.
Showing 1–100 of 105 benchmarks.
- Dtbench Accuracy170 models
- Dtbench CRI-rescaled score170 models
- Lmca141 models
- Forecastbench Dataset score85 models
- Forecastbench Market score85 models
- Forecastbench Overall score85 models
- Proofbench83 models
- HELM Lite: Mean win rate69 models
- HELM Lite: NarrativeQA - F169 models
- LiveBench Data Analysis42 models
- LiveBench IF42 models
- LiveBench Language42 models
- LiveBench Overall42 models
- Enigma Eval41 models
- Blueprint Bench 2 Raw score40 models
- Blueprint Bench 2 Score40 models
- Furniture Assembly40 models
- Mirrorcode39 models
- Ebr Bench32 models
- Gbaeval Overall score28 models
- Gbaeval Procedural score28 models
- Gbaeval Replay score28 models
- Weirdml V3 Max performance27 models
- Weirdml V3 Runs27 models
- Weirdml V3 Score27 models
- Surface Evolver Bench Mean score26 models
- Surface Evolver Bench Pass rate26 models
- Artificial Analysis14 models
- Spireclimb11 models
- Spireclimb Sts1 A20 Heart11 models
- Spireclimb Sts2 A1011 models
- ANLI10 models
- Btf3 Binary Brier10 models
- Btf3 Numeric RPS10 models
- Btf3 Pooled score10 models
- Exploitbench Envs8 models
- Exploitbench Episodes8 models
- Exploitbench Mean8 models
- Exploitbench Mean capability8 models
- Exploitbench T1 reach8 models
- Exploitbench T2 reach8 models
- Exploitbench T3 reach8 models
- Exploitbench T4 reach8 models
- Exploitbench T5 reach8 models
- Spatialviz Bench Overall score8 models
- LAMBADA5 models
- MLVU-M5 models
- AA-Index4 models
- SQuALITY4 models
- CoVoST23 models
- Translation en→Set1 COMET223 models
- Translation en→Set1 spBleu3 models
- Translation Set1→en COMET223 models
- Translation Set1→en spBleu3 models
- IF2 models
- Mindcube Among score2 models
- Mindcube Around score2 models
- Mindcube Overall score2 models
- Mindcube Rotation score2 models
- MultiLF2 models
- CoVoST2 en-zh1 model
- DS-FIM-Eval1 model
- LongFact1 model