Skip to content
Model Pareto

GPT-6 Astra

OpenAIProprietaryopenai.com ↗
Compare with nearest rivalsCompare with…
Input
$10/M tok
Output
$50/M tok
Blended
$20/M tok · 3:1
Speed
52tok/s
Context
1Mtokens

Rankings

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

SWE-bench VerifiedEstimated
~#2 of 14 (estimated)~90.0%
  1. #1Claude Opus 596.0%
  2. ~#2GPT-6 AstraEstimated90.0%
  3. #2Claude Sonnet 585.2%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#5 of 19 (estimated)~75.1%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #4Claude Opus 579.2%
  4. ~#5GPT-6 AstraEstimated75.1%
  5. #5Intern-S2-397B68.5%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#2 of 20 (estimated)~92.3%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. ~#2GPT-6 AstraEstimated92.3%
  3. #2Qwen3.8 Flash-Next91.9%
No published score — estimated from related benchmarks

Writing & chat

IFBenchEstimated
~#3 of 126 (estimated)~81.9%
  1. #1MiniMax-M382.9%
  2. #2Qwen3.8 2.4T A95B82.8%
  3. ~#3GPT-6 AstraEstimated81.9%
  4. #3Qwen3.8-Omni-Flash81.5%
No published score — estimated from related benchmarks
MMMLUEstimated
~#2 of 5 (estimated)~91.4%
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2GPT-6 AstraEstimated91.4%
  3. #2Gemma 4 31B88.4%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Few votesVerified
#14 of 531460 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #13MiMo-V2.6-Pro1461
  4. #14GPT-6 AstraFew votes1460
  5. #15GPT-5.6 Terra1456
lmarena.ai · 2026-09-24
LMArena Text (Elo)Few votesVerified
#10 of 531480 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #10GLM-5.31480
  4. #10GPT-6 AstraFew votes1480
  5. #10MiMo-V2.6-Pro1480
lmarena.ai · 2026-09-24

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2GPT-6 AstraEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~#2 of 9 (estimated)~86.1%
  1. #1Gemini 3.8 Flash86.2%
  2. ~#2GPT-6 AstraEstimated86.1%
  3. #2Kimi K384.8%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#2 of 8 (estimated)~91.4%
  1. #1MiniMax-M391.6%
  2. ~#2GPT-6 AstraEstimated91.4%
  3. #2Kimi K391.1%
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#2 of 25 (estimated)~96.9%
  1. #1Inkling97.1%
  2. ~#2GPT-6 AstraEstimated96.9%
  3. #2Muse Glimmer94.7%
No published score — estimated from related benchmarks

Agents

τ²-bench (Telecom)Estimated
~#2 of 116 (estimated)~98.3%
  1. #1Step 3.7 Flash98.5%
  2. ~#2GPT-6 AstraEstimated98.3%
  3. #2Gemini 3.1 Pro95.6%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#3 of 12 (estimated)~83.4%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. ~#3GPT-6 AstraEstimated83.4%
  4. #3Nex-N2.5-Pro82.2%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~55.0%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3GPT-6 AstraEstimated55.0%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
Not comparable across labs (1)

Kept for reference, not counted in rankings: these use a lab-specific task set, answer key or scoring, so scores can't be compared fairly across labs. Only published scores are shown.