Skip to content

Benchmarks

Sources
8
Entries tracked
22,310
Last sync
50 min
All sources syncing normally
  • Arena · Text4 hours ago
  • Arena · WebDev4 hours ago
  • Arena · Vision4 hours ago
  • Arena · Agent4 hours ago
  • GPQA Diamond50 minutes ago
  • SWE-bench50 minutes ago
  • Terminal-Bench50 minutes ago
  • ARC-AGI-250 minutes ago

deepseek-v4-flash-0731

62±2

59interval64

DeepSeekJul 2026swing #45–#244

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) ×15 of 1034 models
ModelOrgIntervalSwingiiiiiiiiiiiiiiiiiiiiiiAdd to compare
108DeepSeek V4 Flash 0420 (Max)deepseek——61.8 97.2Ranked 61.8 = (1 × 97.2 + 3 × 50) ÷ 4. 97.2 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—————————————————————97—
112deepseek-v4-flash-0731DeepSeekJul 2026$0.01 / $0.4561.7 68.7Ranked 61.7 = (5 × 68.7 + 3 × 50) ÷ 8. 68.7 is the mean percentile over the 5 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.59–64575/22#45–244———————8779—3072—75————————
184deepseek-v4-flashdeepseekJul 2026$0.01 / $0.4558.5 62.7Ranked 58.5 = (6 × 62.7 + 3 × 50) ÷ 9. 62.7 is the mean percentile over the 6 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.57–60356/22#42–1847778—51—————————4374—————54—
333deepseek-v4-flash-high-previewdeepseekOct 2026—52.8 55.7Ranked 52.8 = (3 × 55.7 + 3 × 50) ÷ 6. 55.7 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.51–55343/22#80–3337845—44——————————————————
449DeepSeek-V4-Flash Preview (High)deepseekOct 2026—49.0 46.0Ranked 49.0 = (1 × 46.0 + 3 × 50) ÷ 4. 46.0 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.48–51—1/22low#79–449—46————————————————————

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.