Skip to content

Benchmarks

Sources
8
Entries tracked
22,310
Last sync
52 min
All sources syncing normally
  • Arena · Text3 hours ago
  • Arena · WebDev3 hours ago
  • Arena · Vision3 hours ago
  • Arena · Agent3 hours ago
  • GPQA Diamond52 minutes ago
  • SWE-bench52 minutes ago
  • Terminal-Bench52 minutes ago
  • ARC-AGI-252 minutes ago

Command R7B (FC)

49±0

49interval50

cohereswing #434–#434

Overall ×1WebDev Arena ×1Vision Arena ×1Factuality Arena ×1Search Arena ×1Document Arena ×1Agent Arena ×1GPQA Diamond ×1AIME (math) ×1FrontierMath ×1SimpleQA Verified ×1ARC-AGI-2 ×1Humanity's Last Exam ×1SimpleBench ×1LiveBench ×1BFCL v4 (function calling) ×1dormantSWE-bench Verified (live board) ×1Terminal-Bench 4.0 ×1MMLU-Pro (Artificial Analysis) ×1LiveCodeBench (Artificial Analysis) ×1IFBench (Artificial Analysis) ×1HHEM Hallucination (Vectara) ×18 of 1034 models
ModelOrgIntervalSwingiiiiiiiiiiiiiiiiiiiiiiAdd to compare
434Command R7B (FC)cohere——49.4 47.6Ranked 49.4 = (1 × 47.6 + 3 × 50) ÷ 4. 47.6 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.——1/22low————————————————48——————
575command-r-plus-08-2024cohereAug 2024$2.50 / $1045.0 40.0Ranked 45.0 = (3 × 40.0 + 3 × 50) ÷ 6. 40.0 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.44–46533/22#293–57528—————————————20——————72
756command-r-plus-04-2024Cohere——40.6 12.4Ranked 40.6 = (1 × 12.4 + 3 × 50) ÷ 4. 12.4 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.——1/22low———————————————12———————
828command-r-03-2024Cohere——38.9 5.5Ranked 38.9 = (1 × 5.5 + 3 × 50) ÷ 4. 5.5 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.——1/22low———————————————5———————
845command-r-pluscohereApr 2024—38.5 21.3Ranked 38.5 = (2 × 21.3 + 3 × 50) ÷ 5. 21.3 is the mean percentile over the 2 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.38–3982/22low#304–84526—————————————17———————
869c4ai-command-r-plus-08-2024Cohere,Cohere Labs (formerly Cohere for AI)——38.1 2.3Ranked 38.1 = (1 × 2.3 + 3 × 50) ÷ 4. 2.3 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.——1/22low——————————————2————————
878command-r-08-2024cohereAug 2024$0.15 / $0.6037.9 19.7Ranked 37.9 = (2 × 19.7 + 3 × 50) ÷ 5. 19.7 is the mean percentile over the 2 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.37–3892/22low#298–87824—————————————15———————
1004command-rcohereMar 2024—29.6 14.3Ranked 29.6 = (4 × 14.3 + 3 × 50) ÷ 7. 14.3 is the mean percentile over the 4 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.29–30114/22#325–100421—————————————10———1214——

Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model

The few things in AI and quantum that actually mattered this week — honestly summarised.

One email a week. Unsubscribe in one click. No tracking, no sharing.