GPT-5.5
- Input
- $5.00/M tok
- Output
- $30/M tok
- Blended
- $11.3/M tok · 3:1
- Speed
- 91tok/s
- Context
- 922Ktokens
- Cost per task
- ~$13/taskest.
Previous generation.
Rankings
Coding
Mixed#46 / 137rank by quality59.8±5.3quality / 1004/7 benchmarks measuredWriting & chat
Verified#23 / 162rank by quality74.2±3.3quality / 1004/5 benchmarks measuredVision
Verified#21 / 98rank by quality73.1±4.8quality / 1003/6 benchmarks measuredHard reasoning
Verified#28 / 218rank by quality74.6±3.7quality / 1003/4 benchmarks measuredAgents
Mixed#34 / 187rank by quality66.4±3.2quality / 1007/7 benchmarks measured
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#3 of 21 (estimated)~82.7%
No published score — estimated from related benchmarks
DeepSWE v1.1Lab-reported
#19 of 4567.0%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #18GPT-6 Astra67.6%
- #19GPT-5.567.0%
- #20Gemini 3.8 Flash65.8%
openai.com · 2026-07-09
LiveCodeBenchEstimated
~#10 of 28 (estimated)~83.0%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #9Nemotron 3.5 Super VL NVFP487.4%
- ~#10GPT-5.5Estimated83.0%
- #10Ternary Bonsai 27B82.8%
No published score — estimated from related benchmarks
SciCodeVerified
#25 of 11855.8%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #24DeepSeek V4.1 Flash NVFP455.8%
- #25GPT-5.555.8%
- #26GPT-6.1 Sol55.7%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#20 of 26 (estimated)~42.6
No published score — estimated from related benchmarks
Writing & chat
IFBenchVerified
#20 of 13975.9%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #20GPT-5.4 nano75.9%
- #20GPT-5.575.9%
- #22Qwen3.5 122B A10B75.7%
artificialanalysis.ai · 2026-09-24
LMArena Text, Non-English (Elo)Verified
#9 of 561474 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #8Kimi K31477
- #9GPT-5.51474
- #10Qwen3.8 Max (0902)1470
lmarena.ai · 2026-09-24
#11 of 251844 Elo
eqbench.com · 2026-09-24
Vision
MMMU-ProVerified
#15 of 8779.9%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #13Qwen3.7 Plus80.5%
- #15GPT-5.579.9%
- #16Qwen3.8 Flash-Next79.8%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~#5 of 12 (estimated)~83.1%
- #1Gemini 3.8 Flash86.2%
- #2Kimi K384.8%
- #4Qwen3.8-Omni-Flash83.5%
- ~#5GPT-5.5Estimated83.1%
- #5MiniMax-M3.1-Flash82.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~89.7%
No published score — estimated from related benchmarks
GDP.pdf (AA)Verified
#15 of 4721.2%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #14Claude Opus 521.6%
- #15GPT-5.521.2%
- #16Gemini 3.8 Flash21.0%
artificialanalysis.ai · 2026-09-24
Hard reasoning
Humanity's Last ExamVerified
#20 of 19845.8%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #19Step 5 Preview46.5%
- #20GPT-5.545.8%
- #21Claude Haiku 5.544.4%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#4 of 34 (estimated)~96.6%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #3Inkling97.1%
- ~#4GPT-5.5Estimated96.6%
- #4Ternary Bonsai 2 27B95.8%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#7 of 11993.9%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #6Mistral Medium 3.594.2%
- #7GPT-5.593.9%
- #8Qwen3.5 122B A10B93.6%
artificialanalysis.ai · 2026-09-24
GDPval-AA (Elo)Verified
#30 of 911336 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #29K2 Horizon 375B A23B1361
- #30GPT-5.51336
- #31MiniMax-M31242
artificialanalysis.ai · 2026-09-24