Noometry

Model comparison

Claude Opus 4.7 vs GPT-6 Sol

GPT-6 Sol is the stronger model overall, scoring 61.8 to 58.3 on the Noometry Index.

Last verified . 44 shared benchmarks.

Claude Opus 4.7 Anthropic

58.3

Rank #19 Confirmed

GPT-6 Sol OpenAI

61.8

Rank #12 Confirmed

Summary

  • They share 44 benchmarks with published results for both. Claude Opus 4.7 scores higher in 5 categories and GPT-6 Sol in 5 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Sol leads 87.2 to 66.7.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 31.7% for Claude Opus 4.7 and 90% for GPT-6 Sol.
  • GPT-6 Sol is cheaper at $2 / $10 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.
  • GPT-6 Sol accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Opus 4.7GPT-6 Sol
ProviderAnthropicOpenAI
Noometry Index58.361.8
Released2026-04-142026-09-22
WeightsProprietaryProprietary
Context window1M1.05M
Max output128K128K
Input $ / M tokens$5$2
Output $ / M tokens$25$10
Results tracked6645

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Too close to call

Claude Opus 4.7: 59.6 (#13), GPT-6 Sol: 60.1 (#11)

BenchmarkClaude Opus 4.7GPT-6 Sol
FrontierCode38.5%49.3%
LMArena WebDev15581688
SciCode54.5%57.6%
LMArena Coding15181447
ALE-Bench1,3232,462
SWE-bench Verified83.5%—
DeepSWE—68.8%
GSO44.1%—
WeirdML76.4%—
MirrorCode31.1%—

Agentic & Tool Use Claude Opus 4.7 leads

Claude Opus 4.7: 47.9 (#10), GPT-6 Sol: 37.2 (#36)

BenchmarkClaude Opus 4.7GPT-6 Sol
APEX-Agents49.2%54.3%
GDP.pdf21%26.4%
Vending-Bench 210,93714,428
Terminal-Bench80.2%—
OSWorld 2.018.2%—
τ²-bench Banking40.2%—
PostTrainBench28.6%—
ExploitBench26.5%—
GBAEval43.8%—
LMArena Search1233—

Reasoning GPT-6 Sol leads

Claude Opus 4.7: 53.8 (#29), GPT-6 Sol: 74.0 (#9)

BenchmarkClaude Opus 4.7GPT-6 Sol
ARC-AGI-275.8%89.6%
NYT Connections (extended)39%90.1%
ARC-AGI-193.5%95.5%
CritPt12%30.9%
EBR-Bench19%53.3%
LMArena Hard Prompts15061418
Mystery Game Puzzles28%56%
DTBench94.7%97.3%
LMCA52.2%59.1%
Epoch Capabilities Index156.25162.72
SimpleBench61.7%—
Kagi LLM Benchmark80.7%—
Chess Puzzles30%—
Thematic Generalization72.8%—
ForecastBench60.3—

Math GPT-6 Sol leads

Claude Opus 4.7: 66.7 (#26), GPT-6 Sol: 87.2 (#7)

BenchmarkClaude Opus 4.7GPT-6 Sol
FrontierMath (Tiers 1-3)70.2%89.8%
FrontierMath Tier 431.7%90%
OTIS Mock AIME 2024-202597.8%100%
ProofBench54%83%
LMArena Math14991402
MathArena Final-Answer Competitions73.6%—
FrontierMath (Feb 2025 set)43.8%—
FrontierMath Tier 4 (v1)22.9%—

Knowledge GPT-6 Sol leads

Claude Opus 4.7: 62.6 (#23), GPT-6 Sol: 64.8 (#15)

BenchmarkClaude Opus 4.7GPT-6 Sol
GPQA Diamond90.2%94.3%
SimpleQA Verified51.7%60.7%
Vectara Hallucination Rate12%6.5%
LMArena Expert15211439
Humanity's Last Exam36.2%—

Multimodal GPT-6 Sol leads

Claude Opus 4.7: 41.2 (#38), GPT-6 Sol: 47.6 (#10)

BenchmarkClaude Opus 4.7GPT-6 Sol
LMArena Vision13161245
Blueprint-Bench 224.5%36.9%
Furniture Assembly33.3%58.3%
LMArena Document1495—

Multilingual Claude Opus 4.7 leads

Claude Opus 4.7: 57.3 (#10), GPT-6 Sol: 50.5 (#118)

BenchmarkClaude Opus 4.7GPT-6 Sol
LMArena Non-English14801385
LMArena Chinese15311405
LMArena French15031410
LMArena German14951390
LMArena Japanese14721385
LMArena Korean14641341
LMArena Russian14941401
LMArena Spanish14951384

Instruction Following Claude Opus 4.7 leads

Claude Opus 4.7: 78.4 (#10), GPT-6 Sol: 74.5 (#94)

BenchmarkClaude Opus 4.7GPT-6 Sol
LMArena Instruction Following14981412

Long Context Claude Opus 4.7 leads

Claude Opus 4.7: 46.2 (#25), GPT-6 Sol: 43.1 (#108)

BenchmarkClaude Opus 4.7GPT-6 Sol
LMArena Longer Query15051411

Writing & Preference Claude Opus 4.7 leads

Claude Opus 4.7: 75.1 (#8), GPT-6 Sol: 71.9 (#18)

BenchmarkClaude Opus 4.7GPT-6 Sol
LMArena Text14901395
LMArena Creative Writing14861378
EQ-Bench Creative Writing19142125
LMArena Multi-Turn15051412
EQ-Bench 41311—

Frequently asked questions

Is Claude Opus 4.7 better than GPT-6 Sol?

GPT-6 Sol is the stronger model overall, scoring 61.8 to 58.3 on the Noometry Index.

Which is cheaper, Claude Opus 4.7 or GPT-6 Sol?

GPT-6 Sol is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Claude Opus 4.7 lists at $5 and $25.

Is Claude Opus 4.7 or GPT-6 Sol better for coding?

They score almost the same on coding (59.6 vs 60.1); test both on your own repository before choosing.

Which has the bigger context window?

GPT-6 Sol does, with 1.05M tokens against 1M.

How many benchmarks do Claude Opus 4.7 and GPT-6 Sol share?

44 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and GPT-6 Sol has 45.

Related comparisons

Go deeper