Skip to content

Benchmarks

Sources
8
Entries tracked
22,308
Last sync
12 min
All sources syncing normally
  • Arena · Text11 hours ago
  • Arena · WebDev11 hours ago
  • Arena · Vision11 hours ago
  • Arena · Agent11 hours ago
  • GPQA Diamond12 minutes ago
  • SWE-bench12 minutes ago
  • Terminal-Bench12 minutes ago
  • ARC-AGI-212 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) ×11 of 1034 models
ModelOrgIntervalSwingiiiiiiiiiiiiiiiiiiiiiiAdd to compare
112deepseek-v4-flash-0731DeepSeekJul 2026$0.00 / $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————————

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.