Skip to content

Benchmarks

Sources
8
Entries tracked
22,310
Last sync
51 min
All sources syncing normally
  • Arena · Text4 hours ago
  • Arena · WebDev4 hours ago
  • Arena · Vision4 hours ago
  • Arena · Agent4 hours ago
  • GPQA Diamond51 minutes ago
  • SWE-bench51 minutes ago
  • Terminal-Bench51 minutes ago
  • ARC-AGI-251 minutes ago

deepseek-r1-local

56±0

56interval57

DeepSeekswing #244–#244

deepseek-r1-local-2

55±0

55interval56

DeepSeekswing #265–#265

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) ×110 of 1034 models
ModelOrgIntervalSwingiiiiiiiiiiiiiiiiiiiiiiAdd to compare
243deepseek-r1-0528deepseekMay 2025$0.50 / $2.1556.3 58.4Ranked 56.3 = (9 × 58.4 + 3 × 50) ÷ 12. 58.4 is the mean percentile over the 9 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.55–58729/22#88–25070——————5747——19—3480———918740—
244deepseek-r1-localDeepSeek——56.3 75.3Ranked 56.3 = (1 × 75.3 + 3 × 50) ÷ 4. 75.3 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———————————————75———————
265deepseek-r1-local-2DeepSeek——55.4 71.5Ranked 55.4 = (1 × 71.5 + 3 × 50) ÷ 4. 71.5 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———————————————71———————
389deepseek-r1deepseekJan 2025$0.70 / $2.5050.7 51.0Ranked 50.7 = (10 × 51.0 + 3 × 50) ÷ 13. 51.0 is the mean percentile over the 10 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.50–526610/22#117–38962——————5140——24—2486———89653831
643DeepSeek-R1-Distill-Llama-70BDeepSeekJan 2025$0.80 / $0.8043.3 40.0Ranked 43.3 = (6 × 40.0 + 3 × 50) ÷ 9. 40.0 is the mean percentile over the 6 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.42–45526/22#286–643———————3839—————53———653213—
778DeepSeek-R1-Distill-Qwen-32BDeepSeek——40.1 35.1Ranked 40.1 = (6 × 35.1 + 3 × 50) ÷ 9. 35.1 is the mean percentile over the 6 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.39–41416/22#255–778———————4541—————37———48336—
812DeepSeek-R1-Distill-Qwen-14BDeepSeek——39.2 32.8Ranked 39.2 = (5 × 32.8 + 3 × 50) ÷ 8. 32.8 is the mean percentile over the 5 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.38–41435/22#347–812———————2638—————————48475—
919deepseek-r1-0528-qwen3-8bdeepseek——36.7 28.7Ranked 36.7 = (5 × 28.7 + 3 × 50) ÷ 8. 28.7 is the mean percentile over the 5 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.36–37565/22#465–919———————036—————————48572—
961DeepSeek R1 Distill Llama 8Bdeepseek——33.5 17.0Ranked 33.5 = (3 × 17.0 + 3 × 50) ÷ 6. 17.0 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.—273/22———————————————————21292—
1029DeepSeek-R1-Distill-Qwen-1.5BDeepSeek——25.5 10.7Ranked 25.5 = (5 × 10.7 + 3 × 50) ÷ 8. 10.7 is the mean percentile over the 5 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.24–26295/22#407–1029———————1430—————————361—

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.