GPT-6 Astra
- Input
- $10/M tok
- Output
- $50/M tok
- Blended
- $20/M tok · 3:1
- Speed
- 52tok/s
- Context
- 1Mtokens
- Cost per task
- $6.2/task · AA
Rankings
Coding
Verified#11 / 137rank by quality83.4±4.5quality / 1004/7 benchmarks measuredWriting & chat
Verified#3 / 162rank by quality89.3±5.3quality / 1003/5 benchmarks measuredSpeed frontierVision
Verified#1 / 98rank by quality97.2±3.8quality / 1003/6 benchmarks measuredPrice frontierSpeed frontierHard reasoning
Verified#8 / 218rank by quality87.6±3.7quality / 1003/4 benchmarks measuredAgents
Mixed#16 / 187rank by quality80.6±4.6quality / 1004/7 benchmarks measured
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#2 of 21 (estimated)~89.1%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#6 of 24 (estimated)~75.7%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #5Claude Opus 579.2%
- ~#6GPT-6 AstraEstimated75.7%
- #6Intern-S2-397B68.5%
No published score — estimated from related benchmarks
DeepSWE v1.1Verified
#18 of 4567.6%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #17MiMo-V2.6-Flash67.9%
- #18GPT-6 Astra67.6%
- #19GPT-5.567.0%
artificialanalysis.ai · 2026-09-24
Terminal-Bench 4.0Verified
#5 of 10159.1%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #3Claude Opus 5.559.6%
- #5GPT-6 Astra59.1%
- #6Gemini 4 Argon57.1%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#5 of 28 (estimated)~89.7%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #4Ternary Bonsai 2 27B90.1%
- ~#5GPT-6 AstraEstimated89.7%
- #5Nemotron 3 Ultra89.0%
No published score — estimated from related benchmarks
SciCodeVerified
#21 of 11856.5%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #20Gemini 3.8 Flash56.6%
- #21GPT-6 Astra56.5%
- #22Claude Opus 556.4%
artificialanalysis.ai · 2026-09-24
Writing & chat
LMArena Text, Non-English (Elo)Few votesVerified
#12 of 561463 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #12GLM-5.3 Flash1463
- #12GPT-6 AstraFew votes1463
- #15MiMo-V2.6-Pro1461
lmarena.ai · 2026-10-02
LMArena Text (Elo)Few votesVerified
#14 of 561477 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #12MiMo-V2.6-Pro1480
- #14GPT-6 AstraFew votes1477
- #15GLM-5.3 Flash1475
lmarena.ai · 2026-10-02
#1 of 252173 Elo
eqbench.com · 2026-09-24
Vision
CharXiv ReasoningEstimated
~#2 of 12 (estimated)~86.1%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#2 of 8 (estimated)~91.4%
No published score — estimated from related benchmarks
Hard reasoning
Humanity's Last ExamVerified
#7 of 19854.7%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #6Claude Opus 554.9%
- #7GPT-6 Astra54.7%
- #8Muse Wonder Full53.6%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#2 of 34 (estimated)~99.3%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Estimated
~#3 of 120 (estimated)~98.2%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- ~#3GPT-6 AstraEstimated98.2%
- #3Gemini 3.1 Pro95.6%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#3 of 15 (estimated)~83.6%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~55.3%
No published score — estimated from related benchmarks
AutomationBench-AAVerified
#5 of 8468.5%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #4DeepSeek V4.1 Flash68.9%
- #5GPT-6 Astra68.5%
- #6Muse Wonder68.1%
artificialanalysis.ai · 2026-09-24
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.