GPT-6.1 Sol
- Input
- $2.00/M tok
- Output
- $10/M tok
- Blended
- $4.00/M tok · 3:1
- Speed
- 53tok/s
- Context
- 922Ktokens
- Cost per task
- $1.3/task · AA
Context: 1.05M total, 922k max input (1.05M minus 128k output), same basis as gpt-6-sol's 872k. OpenAI says a faster "Ultrafast" serving tier of Sol is coming soon (up to 8x faster tokens in Codex at roughly 6x the price; https://thenextweb.com/news/openai-gpt-6-1-sol-price-astra-devday); same weights, so it will be a serving tier rather than a separate model.
Rankings
Coding
Verified#12 / 137rank by quality83.2±4.5quality / 1004/7 benchmarks measuredWriting & chat
Verified#8 / 162rank by quality81.7±6.0quality / 1002/5 benchmarks measuredVision
Verified#6 / 98rank by quality91.0±6.3quality / 1002/6 benchmarks measuredPrice frontierHard reasoning
Verified#12 / 218rank by quality85.3±5.1quality / 1002/4 benchmarks measuredAgents
Verified#15 / 187rank by quality81.1±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)~89.2%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#6 of 24 (estimated)~75.5%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #5Claude Opus 579.2%
- ~#6GPT-6.1 SolEstimated75.5%
- #6Intern-S2-397B68.5%
No published score — estimated from related benchmarks
DeepSWE v1.1Verified
#8 of 4573.2%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #7MiniMax-M3.1-Flash73.7%
- #8GPT-6.1 Sol73.2%
- #9Grok 4.772.6%
artificialanalysis.ai · 2026-10-02
Terminal-Bench 4.0Verified
#8 of 10156.1%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #6Muse Wonder Full57.1%
- #8GPT-6.1 Sol56.1%
- #9Claude Fable 5.152.0%
artificialanalysis.ai · 2026-09-29
LiveCodeBenchEstimated
~#6 of 28 (estimated)~88.3%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #5Nemotron 3 Ultra89.0%
- ~#6GPT-6.1 SolEstimated88.3%
- #6Beam 1.0 501B A23B88.3%
No published score — estimated from related benchmarks
SciCodeVerified
#26 of 11855.7%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #25GPT-5.555.8%
- #26GPT-6.1 Sol55.7%
- #27Claude Haiku 5.555.0%
artificialanalysis.ai · 2026-09-29
Writing & chat
LMArena Text, Non-English (Elo)Verified
#11 of 561469 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #10Qwen3.8 Max (0902)1470
- #11GPT-6.1 Sol1469
- #12GLM-5.31463
lmarena.ai · 2026-10-02
EQ-Bench Creative Writing v3 (Elo)Estimated
~#8 of 26 (estimated)~2010 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #7Claude Opus 5.52050
- ~#8GPT-6.1 SolEstimated2010
- #8Grok 4.72007
No published score — estimated from related benchmarks
Vision
CharXiv ReasoningEstimated
~#2 of 12 (estimated)~85.6%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#2 of 8 (estimated)~91.1%
No published score — estimated from related benchmarks
ChartographyEstimated
~#5 of 25 (estimated)~47.5%
- #1Claude Fable 5.273.4%
- #2GPT-6 Astra71.0%
- #4GPT-6 Sol53.6%
- ~#5GPT-6.1 SolEstimated47.5%
- #5Claude Haiku 5.546.4%
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondEstimated
~#2 of 193 (estimated)~95.5%
No published score — estimated from related benchmarks
Humanity's Last ExamVerified
#9 of 19852.9%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #8Muse Wonder Full53.6%
- #9GPT-6.1 Sol52.9%
- #10Kimi K3.1 Pro52.5%
artificialanalysis.ai · 2026-09-29
AIME (latest)Estimated
~#2 of 34 (estimated)~99.1%
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-6.1 SolEstimated98.2%
- #3Gemini 3.1 Pro95.6%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#3 of 15 (estimated)~83.8%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~57.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#4 of 22 (estimated)~90.9%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #3Kimi K391.2%
- ~#4GPT-6.1 SolEstimated90.9%
- #4Claude Opus 590.8%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#17 of 911592 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #16Qwen3.8 2.4T A95B1597
- #17GPT-6.1 Sol1592
- #18Step 5 Preview1584
artificialanalysis.ai · 2026-10-10
τ-Bench Banking (AA)Estimated
~#11 of 91 (estimated)~44.7%
- #1Muse Spark 1.350.5%
- #2GLM-5.350.3%
- #10Gemini 3.8 Flash44.9%
- ~#11GPT-6.1 SolEstimated44.7%
- #11Grok 4.643.3%
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.