Sign in

Is GPT-6.2 Astra SOTA in Reasoning?#54 in ReasoningRanked #54 in Reasoning.

How it scores here

GPT-6.2 Astra in Reasoning

Primary benchmarks

  • GPQA Diamond: 96.8% (CI 94.4%–99.2%) on Nov 17, 2026 (#1 of 245).
  • LMArena Text (style-controlled, hard prompts): 1485 (CI 1469–1501) on Nov 19, 2026 (#66 of 263).

On the category's weighted score it is 32.4 points behind #1 Gemini 4 Carbon and 0.6 behind the next model up, Kimi K2 6. At $16.00 per 1M tokens, 42 of 111 priced models rank higher in Reasoning for the same price or less.

Nearby on the board

#ModelCategory score
51Ernie 5.169.4
52Claude Sonnet 4.568.8
53Kimi K2 668.2
54GPT-6.2 Astra67.6
55Grok 4.20 Multi Agent Beta67.1
56GPT-6 Sol66.5
57Qwen3 6 Max Preview65.9
Standings

Reasoning

#ModelState
1Gemini 4 CarbonCo-SOTA
1Gemini 4 ArgonCo-SOTA
1Gemini 4 NeonCo-SOTA
2Muse WonderNear-SOTA
3Claude Opus 4.6Near-SOTA
4Claude Opus 5.5Near-SOTA
5Claude Fable 5Near-SOTA
6Claude Opus 4.7Was SOTA
7Claude Fable 5.1Was SOTA
8Muse Spark 1.3#8 in this category
9Gemini 3.8 Flash#9 in this category
10Claude Fable 5.2#10 in this category

Category page →