Noometry

Model comparison

Claude Opus 4.7 vs GPT-5.1

Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 49.0 on the Noometry Index. GPT-5.1 costs 2.9× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Last verified . 45 shared benchmarks.

Claude Opus 4.7 Anthropic

58.3

Rank #19 Confirmed

GPT-5.1 OpenAI

49.0

Rank #53 Confirmed

Summary

  • They share 45 benchmarks with published results for both. Claude Opus 4.7 scores higher in 7 categories and GPT-5.1 in 3 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where Claude Opus 4.7 leads 47.9 to 32.7.
  • The biggest single-benchmark swing is ARC-AGI-2: 75.8% for Claude Opus 4.7 and 17.6% for GPT-5.1.
  • GPT-5.1 is cheaper at $1.25 / $10 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.
  • Claude Opus 4.7 accepts more context: 1M tokens versus 400K.

Side by side

Claude Opus 4.7GPT-5.1
ProviderAnthropicOpenAI
Noometry Index58.349.0
Released2026-04-142025-11-13
WeightsProprietaryProprietary
Context window1M400K
Max output128K128K
Input $ / M tokens$5$1.25
Output $ / M tokens$25$10
Results tracked6663

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

Category by category

Coding Claude Opus 4.7 leads

Claude Opus 4.7: 59.6 (#13), GPT-5.1: 46.4 (#66)

BenchmarkClaude Opus 4.7GPT-5.1
SWE-bench Verified83.5%68%
LMArena WebDev15581395
SciCode54.5%43.3%
GSO44.1%13.7%
WeirdML76.4%60.8%
LMArena Coding15181454
ALE-Bench1,3231,192
FrontierCode38.5%—
SWE-bench Verified (bash only)—66%
LiveBench Coding—72.5%
MirrorCode31.1%—

Agentic & Tool Use Claude Opus 4.7 leads

Claude Opus 4.7: 47.9 (#10), GPT-5.1: 32.7 (#60)

BenchmarkClaude Opus 4.7GPT-5.1
Terminal-Bench80.2%47.6%
LMArena Search12331199
Vending-Bench 210,9371,473
APEX-Agents49.2%—
OSWorld 2.018.2%—
τ²-bench Banking40.2%—
DeepResearch Bench—42.8%
PostTrainBench28.6%—
ExploitBench26.5%—
GBAEval43.8%—
GDP.pdf21%—

Reasoning Claude Opus 4.7 leads

Claude Opus 4.7: 53.8 (#29), GPT-5.1: 39.8 (#58)

BenchmarkClaude Opus 4.7GPT-5.1
ARC-AGI-275.8%17.6%
SimpleBench61.7%53.2%
ARC-AGI-193.5%72.8%
CritPt12%4.9%
Chess Puzzles30%32%
LMArena Hard Prompts15061457
Mystery Game Puzzles28%19%
DTBench94.7%90.1%
LMCA52.2%43.9%
Epoch Capabilities Index156.25149.64
ForecastBench60.358.1
Kagi LLM Benchmark80.7%—
NYT Connections (extended)39%—
EnigmaEval—11.2%
Thematic Generalization72.8%—
EBR-Bench19%—
LiveBench Reasoning—95.8%
LiveBench Data Analysis—72.1%
LiveBench—78.8%

Math Claude Opus 4.7 leads

Claude Opus 4.7: 66.7 (#26), GPT-5.1: 52.2 (#51)

BenchmarkClaude Opus 4.7GPT-5.1
OTIS Mock AIME 2024-202597.8%88.6%
LMArena Math14991447
FrontierMath (Feb 2025 set)43.8%31%
FrontierMath Tier 4 (v1)22.9%12.5%
FrontierMath (Tiers 1-3)70.2%—
FrontierMath Tier 431.7%—
MathArena Final-Answer Competitions73.6%—
ProofBench54%—
Omni-MATH—46.4%
LiveBench Math—94.5%

Knowledge Claude Opus 4.7 leads

Claude Opus 4.7: 62.6 (#23), GPT-5.1: 50.6 (#71)

BenchmarkClaude Opus 4.7GPT-5.1
GPQA Diamond90.2%87.6%
Humanity's Last Exam36.2%23.7%
SimpleQA Verified51.7%48%
Vectara Hallucination Rate12%10.9%
LMArena Expert15211470
MMLU-Pro—57.9%
GPQA (HELM)—44.2%

Multimodal GPT-5.1 leads

Claude Opus 4.7: 41.2 (#38), GPT-5.1: 44.8 (#19)

BenchmarkClaude Opus 4.7GPT-5.1
LMArena Vision13161250
LMArena Document14951403
VPCT—58.7%
Blueprint-Bench 224.5%—
Furniture Assembly33.3%—

Multilingual Claude Opus 4.7 leads

Claude Opus 4.7: 57.3 (#10), GPT-5.1: 53.8 (#56)

BenchmarkClaude Opus 4.7GPT-5.1
LMArena Non-English14801431
LMArena Chinese15311495
LMArena French15031450
LMArena German14951438
LMArena Japanese14721453
LMArena Korean14641401
LMArena Russian14941435
LMArena Spanish14951433

Instruction Following GPT-5.1 leads

Claude Opus 4.7: 78.4 (#10), GPT-5.1: 83.9 (#1)

BenchmarkClaude Opus 4.7GPT-5.1
LMArena Instruction Following14981443
LiveBench Instruction Following—93.3%
IFEval—93.5%

Long Context GPT-5.1 leads

Claude Opus 4.7: 46.2 (#25), GPT-5.1: 47.6 (#14)

BenchmarkClaude Opus 4.7GPT-5.1
LMArena Longer Query15051447
CL-bench—23.7%
CL-bench Life—17.3%

Writing & Preference Claude Opus 4.7 leads

Claude Opus 4.7: 75.1 (#8), GPT-5.1: 64.5 (#55)

BenchmarkClaude Opus 4.7GPT-5.1
LMArena Text14901443
LMArena Creative Writing14861427
LMArena Multi-Turn15051450
EQ-Bench Creative Writing1914—
WildBench—86.3%
EQ-Bench 41311—
LiveBench Language—80.2%

Frequently asked questions

Is Claude Opus 4.7 better than GPT-5.1?

Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 49.0 on the Noometry Index. GPT-5.1 costs 2.9× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.7 or GPT-5.1?

GPT-5.1 is cheaper. It lists at $1.25 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-5.1 better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.6 versus 46.4 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.7 does, with 1M tokens against 400K.

How many benchmarks do Claude Opus 4.7 and GPT-5.1 share?

45 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and GPT-5.1 has 63.

Related comparisons

Go deeper