Noometry

Model comparison

Claude Opus 4.7 vs Gemini 3.1 Pro Preview

Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 56.7 on the Noometry Index. Gemini 3.1 Pro Preview costs 2.2× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Last verified . 63 shared benchmarks.

Claude Opus 4.7 Anthropic

58.3

Rank #19 Confirmed

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

Summary

  • They share 63 benchmarks with published results for both. Claude Opus 4.7 scores higher in 7 categories and Gemini 3.1 Pro Preview in 3 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 53.8.
  • The biggest single-benchmark swing is NYT Connections (extended): 39% for Claude Opus 4.7 and 97.4% for Gemini 3.1 Pro Preview.
  • Gemini 3.1 Pro Preview is cheaper at $2 / $12 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.
  • Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Opus 4.7Gemini 3.1 Pro Preview
ProviderAnthropicGoogle
Noometry Index58.356.7
Released2026-04-142026-02-19
WeightsProprietaryProprietary
Context window1M1.05M
Max output128K66K
Input $ / M tokens$5$2
Output $ / M tokens$25$12
Results tracked6671

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), Gemini 3.1 Pro Preview: 42.5 (#99)

BenchmarkClaude Opus 4.7Gemini 3.1 Pro Preview
SWE-bench Verified83.5%75.6%
LMArena WebDev15581447
SciCode54.5%58.9%
GSO44.1%22.6%
WeirdML76.4%72.1%
LMArena Coding15181484
MirrorCode31.1%8.9%
ALE-Bench1,3231,161
DeepSWE—11.7%
FrontierCode38.5%—
AlgoTune—2.02

Agentic & Tool Use Claude Opus 4.7 leads

Claude Opus 4.7: 47.9 (#10), Gemini 3.1 Pro Preview: 37.7 (#34)

BenchmarkClaude Opus 4.7Gemini 3.1 Pro Preview
Terminal-Bench80.2%80.2%
APEX-Agents49.2%35.3%
τ²-bench Banking40.2%26%
PostTrainBench28.6%22%
ExploitBench26.5%26.1%
GBAEval43.8%0.8%
GDP.pdf21%17%
LMArena Search12331211
Vending-Bench 210,9373,774
OSWorld 2.018.2%—
DeepResearch Bench—47.8%
BALROG—57%
METR Time Horizons—77%

Reasoning Gemini 3.1 Pro Preview leads

Claude Opus 4.7: 53.8 (#29), Gemini 3.1 Pro Preview: 71.7 (#12)

BenchmarkClaude Opus 4.7Gemini 3.1 Pro Preview
ARC-AGI-275.8%77.1%
SimpleBench61.7%79.6%
NYT Connections (extended)39%97.4%
ARC-AGI-193.5%98%
CritPt12%17.7%
Chess Puzzles30%55%
Thematic Generalization72.8%79.4%
EBR-Bench19%14.3%
LMArena Hard Prompts15061485
Mystery Game Puzzles28%34%
DTBench94.7%97.1%
LMCA52.2%53.8%
Epoch Capabilities Index156.25154.77
ForecastBench60.359
Kagi LLM Benchmark80.7%—
EnigmaEval—36.8%

Math Claude Opus 4.7 leads

Claude Opus 4.7: 66.7 (#26), Gemini 3.1 Pro Preview: 62.1 (#34)

BenchmarkClaude Opus 4.7Gemini 3.1 Pro Preview
FrontierMath (Tiers 1-3)70.2%59.6%
FrontierMath Tier 431.7%26.8%
MathArena Final-Answer Competitions73.6%86.5%
OTIS Mock AIME 2024-202597.8%95.6%
ProofBench54%26%
LMArena Math14991485
FrontierMath (Feb 2025 set)43.8%36.9%
FrontierMath Tier 4 (v1)22.9%16.7%

Knowledge Gemini 3.1 Pro Preview leads

Claude Opus 4.7: 62.6 (#23), Gemini 3.1 Pro Preview: 71.8 (#3)

BenchmarkClaude Opus 4.7Gemini 3.1 Pro Preview
GPQA Diamond90.2%94.4%
Humanity's Last Exam36.2%46.4%
SimpleQA Verified51.7%73.5%
Vectara Hallucination Rate12%10.4%
LMArena Expert15211485

Multimodal Claude Opus 4.7 leads

Claude Opus 4.7: 41.2 (#38), Gemini 3.1 Pro Preview: 37.9 (#69)

BenchmarkClaude Opus 4.7Gemini 3.1 Pro Preview
LMArena Vision13161296
Blueprint-Bench 224.5%26.5%
Furniture Assembly33.3%26.7%
LMArena Document14951444

Multilingual Too close to call

Claude Opus 4.7: 57.3 (#10), Gemini 3.1 Pro Preview: 57.0 (#12)

BenchmarkClaude Opus 4.7Gemini 3.1 Pro Preview
LMArena Non-English14801477
LMArena Chinese15311529
LMArena French15031487
LMArena German14951491
LMArena Japanese14721493
LMArena Korean14641455
LMArena Russian14941498
LMArena Spanish14951479

Instruction Following Claude Opus 4.7 leads

Claude Opus 4.7: 78.4 (#10), Gemini 3.1 Pro Preview: 77.0 (#32)

BenchmarkClaude Opus 4.7Gemini 3.1 Pro Preview
LMArena Instruction Following14981466

Long Context Gemini 3.1 Pro Preview leads

Claude Opus 4.7: 46.2 (#25), Gemini 3.1 Pro Preview: 47.4 (#18)

BenchmarkClaude Opus 4.7Gemini 3.1 Pro Preview
LMArena Longer Query15051483
CL-bench—20.8%
CL-bench Life—16.9%

Writing & Preference Claude Opus 4.7 leads

Claude Opus 4.7: 75.1 (#8), Gemini 3.1 Pro Preview: 66.1 (#37)

BenchmarkClaude Opus 4.7Gemini 3.1 Pro Preview
LMArena Text14901481
LMArena Creative Writing14861482
EQ-Bench Creative Writing19141491
EQ-Bench 413111142
LMArena Multi-Turn15051488

Frequently asked questions

Is Claude Opus 4.7 better than Gemini 3.1 Pro Preview?

Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 56.7 on the Noometry Index. Gemini 3.1 Pro Preview costs 2.2× 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 Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview is cheaper. It lists at $2 per million input tokens and $12 per million output tokens; Claude Opus 4.7 lists at $5 and $25.

Is Claude Opus 4.7 or Gemini 3.1 Pro Preview better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.6 versus 42.5 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 1M.

How many benchmarks do Claude Opus 4.7 and Gemini 3.1 Pro Preview share?

63 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and Gemini 3.1 Pro Preview has 71.

Related comparisons

Go deeper