GPT-6 Sol
- Input
- $2.00/M tok
- Output
- $10/M tok
- Blended
- $4.00/M tok · 3:1
- Speed
- 92tok/s
- Context
- 872Ktokens
- Cost per task
- ~$4.2/taskest.
Rankings
Coding
Verified#13 / 137rank by quality80.4±4.5quality / 1004/7 benchmarks measuredWriting & chat
Verified#9 / 162rank by quality79.2±4.3quality / 1003/5 benchmarks measuredVision
Verified#8 / 98rank by quality85.1±4.8quality / 1003/6 benchmarks measuredHard reasoning
Verified#16 / 218rank by quality80.0±5.1quality / 1002/4 benchmarks measuredAgents
Verified#24 / 187rank by quality73.8±7.8quality / 1002/7 benchmarks measured
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#2 of 21 (estimated)~88.9%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#6 of 24 (estimated)~72.8%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #5Claude Opus 579.2%
- ~#6GPT-6 SolEstimated72.8%
- #6Intern-S2-397B68.5%
No published score — estimated from related benchmarks
DeepSWE v1.1Verified
#14 of 4569.0%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #13GPT-5.6 Terra69.6%
- #14GPT-6 Sol69.0%
- #15Claude Opus 5.568.4%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#10 of 28 (estimated)~86.5%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #9Nemotron 3.5 Super VL NVFP487.4%
- ~#10GPT-6 SolEstimated86.5%
- #10Ternary Bonsai 27B82.8%
No published score — estimated from related benchmarks
SciCodeVerified
#18 of 11857.6%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #17GLM-5.3 Flash NVFP457.7%
- #18GPT-6 Sol57.6%
- #19Grok 4.757.4%
artificialanalysis.ai · 2026-09-24
Writing & chat
IFBenchEstimated
~#17 of 140 (estimated)~77.7%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #16Qwen3.7 Plus78.0%
- ~#17GPT-6 SolEstimated77.7%
- #17DeepSeek V4.1 Flash NVFP477.3%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Verified
#22 of 561444 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #21Gemini 3.5 Flash-Lite1445
- #22GPT-6 Sol1444
- #23Qwen3.7 Plus1443
lmarena.ai · 2026-10-02
LMArena Text (Elo)Verified
#20 of 561457 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #19Claude Sonnet 51461
- #20GPT-6 Sol1457
- #21Gemini 3.5 Flash-Lite1456
lmarena.ai · 2026-09-25
#4 of 252125 Elo
eqbench.com · 2026-09-24
Vision
MMMU-ProVerified
#7 of 8783.3%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #6Kimi K3.1 Pro83.9%
- #7GPT-6 Sol83.3%
- #8Qwen3.8 Max (0902)82.8%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~#3 of 12 (estimated)~84.7%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~90.7%
No published score — estimated from related benchmarks
GDP.pdf (AA)Verified
#8 of 4724.8%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #6Claude Opus 5.526.2%
- #8GPT-6 Sol24.8%
- #9Claude Fable 5.224.2%
artificialanalysis.ai · 2026-09-24
ChartographyVerified
#4 of 2453.6%
- #1Claude Fable 5.273.4%
- #2GPT-6 Astra71.0%
- #3Claude Opus 5.566.3%
- #4GPT-6 Sol53.6%
- #5Claude Haiku 5.546.4%
surgehq.ai · 2026-09-24
Hard reasoning
GPQA DiamondEstimated
~#4 of 193 (estimated)~93.9%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #3Gemini 3.1 Pro94.1%
- ~#4GPT-6 SolEstimated93.9%
- #4Claude Fable 5.193.7%
No published score — estimated from related benchmarks
Humanity's Last ExamVerified
#15 of 19847.9%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #14MiniMax-M3.1-Flash48.0%
- #15GPT-6 Sol47.9%
- #16Gemini 3.8 Flash47.8%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#2 of 34 (estimated)~98.4%
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 SolEstimated98.2%
- #3Gemini 3.1 Pro95.6%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#5 of 15 (estimated)~82.0%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #4MiMo-V2.6-Pro82.0%
- ~#5GPT-6 SolEstimated82.0%
- #5Claude Sonnet 581.2%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~54.0%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#7 of 22 (estimated)~88.0%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #6Step 5 Preview88.7%
- ~#7GPT-6 SolEstimated88.0%
- #7GPT-5.6 Terra87.5%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#16 of 91 (estimated)~39.4%
- #1Muse Spark 1.350.5%
- #2GLM-5.350.3%
- #15DeepSeek V4 Pro (0813)39.6%
- ~#16GPT-6 SolEstimated39.4%
- #16GPT-5.539.0%
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.