Skip to content

Benchmarks

Sources
8
Entries tracked
22,308
Last sync
2 min
All sources syncing normally
  • Arena · Text41 minutes ago
  • Arena · WebDev41 minutes ago
  • Arena · Vision41 minutes ago
  • Arena · Agent41 minutes ago
  • GPQA Diamond2 minutes ago
  • SWE-bench2 minutes ago
  • Terminal-Bench2 minutes ago
  • ARC-AGI-22 minutes ago
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) ×111 of 1034 models
ModelOrgIntervalSwingiiiiiiiiiiiiiiiiiiiiiiAdd to compare
166Gemini-2.5-Flash-Lite (FC)google—$0.10 / $0.4059.3 64.9Ranked 59.3 = (5 × 64.9 + 3 × 50) ÷ 8. 64.9 is the mean percentile over the 5 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.—455/22————————————————54——54635798
200gemini-2.5-flashgoogleJun 2025$0.30 / $2.5057.9 60.3Ranked 57.9 = (10 × 60.3 + 3 × 50) ÷ 13. 60.3 is the mean percentile over the 10 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.56–595210/22#133–38965—5348—————33———36—85——85775764
273gemini-2.5-flash-preview-04-17Google DeepMind——55.1 60.3Ranked 55.1 = (3 × 60.3 + 3 × 50) ÷ 6. 60.3 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.53–56363/22#215–273————————53———46—82———————
371gemini-2.5-flash-preview-09-2025-highthinkingGoogle——51.6 56.4Ranked 51.6 = (1 × 56.4 + 3 × 50) ÷ 4. 56.4 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———————————————56———————
383gemini-2.5-flash-preview-09-2025googleSep 2025—51.1 52.3Ranked 51.1 = (3 × 52.3 + 3 × 50) ÷ 6. 52.3 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.49–53293/22#141–38364—5835——————————————————
396gemini-2.5-flash-preview-05-20Google DeepMind——50.5 50.9Ranked 50.5 = (4 × 50.9 + 3 × 50) ÷ 7. 50.9 is the mean percentile over the 4 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.49–52624/22#308–396————————51——2541—87———————
411gemini-2.5-flash-06-05-highthinkingGoogle——50.1 50.5Ranked 50.1 = (1 × 50.5 + 3 × 50) ÷ 4. 50.5 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———————————————51———————
426gemini-2.5-flash-lite-preview-06-17-thinkinggoogleJan 2026—49.5 48.7Ranked 49.5 = (2 × 48.7 + 3 × 50) ÷ 5. 48.7 is the mean percentile over the 2 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.48–51132/22low#159–42655—42———————————————————
508gemini-2.5-flash-lite-preview-09-2025-highthinkingGoogle——47.3 39.2Ranked 47.3 = (1 × 39.2 + 3 × 50) ÷ 4. 39.2 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———————————————39———————
515gemini-2.5-flash-lite-highthinkingGoogle——47.1 38.5Ranked 47.1 = (1 × 38.5 + 3 × 50) ÷ 4. 38.5 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———————————————38———————
613gemini-2.5-flash-lite-preview-09-2025-no-thinkinggoogleSep 2025—44.1 38.2Ranked 44.1 = (3 × 38.2 + 3 × 50) ÷ 6. 38.2 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.43–45373/22#170–61356—3920——————————————————

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.