Skip to content

Benchmarks

Sources
8
Entries tracked
22,310
Last sync
55 min
All sources syncing normally
  • Arena · Text4 hours ago
  • Arena · WebDev4 hours ago
  • Arena · Vision4 hours ago
  • Arena · Agent4 hours ago
  • GPQA Diamond55 minutes ago
  • SWE-bench55 minutes ago
  • Terminal-Bench55 minutes ago
  • ARC-AGI-255 minutes ago

qwen3-30b-a3b-thinking

52±0

52interval53

Alibabaswing #352–#352

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) ×16 of 1034 models
ModelOrgIntervalSwingiiiiiiiiiiiiiiiiiiiiiiAdd to compare
168Qwen3 30B A3B 2507 (Reasoning)alibaba——59.2 68.4Ranked 59.2 = (3 × 68.4 + 3 × 50) ÷ 6. 68.4 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.—203/22———————————————————697858—
352qwen3-30b-a3b-thinkingAlibaba——52.2 58.8Ranked 52.2 = (1 × 58.8 + 3 × 50) ÷ 4. 58.8 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———————————————59———————
400qwen3-30b-a3b-thinking-2507AlibabaJul 2025$0.20 / $2.4050.4 51.0Ranked 50.4 = (2 × 51.0 + 3 × 50) ÷ 5. 51.0 is the mean percentile over the 2 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.48–5212/22low#210–400———————5251—————————————
410qwen3-30b-a3b-instruct-2507alibabaJul 2025$0.09 / $0.3050.2 50.3Ranked 50.2 = (4 × 50.3 + 3 × 50) ÷ 7. 50.3 is the mean percentile over the 4 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.49–52244/22#123–41057——————3845——————62——————
453qwen3-30b-a3balibabaApr 2025$0.12 / $0.5048.9 48.4Ranked 48.9 = (6 × 48.4 + 3 × 50) ÷ 9. 48.4 is the mean percentile over the 6 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.48–50176/22#187–45342——————4345—————————595644—
481Qwen3 30B A3B 2507 Instructalibaba——48.3 46.7Ranked 48.3 = (3 × 46.7 + 3 × 50) ÷ 6. 46.7 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.—363/22———————————————————595823—

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.