Noometry

Model comparison

Claude Opus 4.7 vs DeepSeek-V3.1-Terminus

Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 42.6 on the Noometry Index. DeepSeek-V3.1-Terminus costs 21× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Last verified . 16 shared benchmarks.

Claude Opus 4.7 Anthropic

58.4

Rank #17 Confirmed

DeepSeek-V3.1-Terminus DeepSeek

42.6

Rank #96 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Claude Opus 4.7 scores higher in 7 categories and DeepSeek-V3.1-Terminus in 0 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 4.7 leads 66.5 to 35.7.
  • The biggest single-benchmark swing is LMCA: 52.2% for Claude Opus 4.7 and 28.6% for DeepSeek-V3.1-Terminus.
  • DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.
  • Claude Opus 4.7 accepts more context: 1M tokens versus 164K.
  • DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.7DeepSeek-V3.1-Terminus
ProviderAnthropicDeepSeek
Noometry Index58.442.6
Released2026-04-142025-09-22
WeightsProprietaryOpen
Context window1M164K
Max output128K66K
Input $ / M tokens$5$0.30
Output $ / M tokens$25$1
Results tracked6616

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: 59.9 (#10), DeepSeek-V3.1-Terminus: 41.5 (#114)

BenchmarkClaude Opus 4.7DeepSeek-V3.1-Terminus
SciCode54.5%40.6%
LMArena Coding15191426
ALE-Bench1,323745.17
SWE-bench Verified83.5%—
FrontierCode38.5%—
LMArena WebDev1557—
GSO44.1%—
WeirdML76.4%—
MirrorCode31.1%—

Agentic & Tool Use Not comparable

Claude Opus 4.7: 47.9 (#8), DeepSeek-V3.1-Terminus: —

BenchmarkClaude Opus 4.7DeepSeek-V3.1-Terminus
Terminal-Bench80.2%—
APEX-Agents49.2%—
OSWorld 2.018.2%—
τ²-bench Banking40.2%—
PostTrainBench28.6%—
ExploitBench26.5%—
GBAEval43.8%—
GDP.pdf21%—
LMArena Search1233—
Vending-Bench 210,937—

Reasoning Claude Opus 4.7 leads

Claude Opus 4.7: 53.7 (#24), DeepSeek-V3.1-Terminus: 25.7 (#126)

BenchmarkClaude Opus 4.7DeepSeek-V3.1-Terminus
Kagi LLM Benchmark80.7%57.4%
CritPt12%1.7%
LMArena Hard Prompts15071427
DTBench94.7%81.3%
LMCA52.2%28.6%
ARC-AGI-275.8%—
SimpleBench61.7%—
NYT Connections (extended)39%—
ARC-AGI-193.5%—
Chess Puzzles30%—
Thematic Generalization72.8%—
EBR-Bench19%—
Mystery Game Puzzles28%—
Epoch Capabilities Index156.39—
ForecastBench60.3—

Math Claude Opus 4.7 leads

Claude Opus 4.7: 66.5 (#20), DeepSeek-V3.1-Terminus: 35.7 (#138)

BenchmarkClaude Opus 4.7DeepSeek-V3.1-Terminus
LMArena Math14991402
FrontierMath (Tiers 1-3)70.2%—
FrontierMath Tier 431.7%—
MathArena Final-Answer Competitions73.6%—
OTIS Mock AIME 2024-202597.8%—
ProofBench54%—
FrontierMath (Feb 2025 set)43.8%—
FrontierMath Tier 4 (v1)22.9%—

Knowledge Not comparable

Claude Opus 4.7: 62.6 (#20), DeepSeek-V3.1-Terminus: —

BenchmarkClaude Opus 4.7DeepSeek-V3.1-Terminus
GPQA Diamond90.2%—
Humanity's Last Exam36.2%—
SimpleQA Verified51.7%—
Vectara Hallucination Rate12%—
LMArena Expert1521—

Multimodal Not comparable

Claude Opus 4.7: 41.5 (#29), DeepSeek-V3.1-Terminus: —

BenchmarkClaude Opus 4.7DeepSeek-V3.1-Terminus
LMArena Vision1317—
Blueprint-Bench 224.5%—
Furniture Assembly33.3%—
LMArena Document1495—

Multilingual Claude Opus 4.7 leads

Claude Opus 4.7: 57.5 (#9), DeepSeek-V3.1-Terminus: 52.3 (#87)

BenchmarkClaude Opus 4.7DeepSeek-V3.1-Terminus
LMArena Non-English14811407
LMArena Russian14941434
LMArena Chinese1530—
LMArena French1505—
LMArena German1494—
LMArena Japanese1472—
LMArena Korean1466—
LMArena Spanish1497—

Instruction Following Claude Opus 4.7 leads

Claude Opus 4.7: 78.6 (#9), DeepSeek-V3.1-Terminus: 74.4 (#96)

BenchmarkClaude Opus 4.7DeepSeek-V3.1-Terminus
LMArena Instruction Following14981406

Long Context Claude Opus 4.7 leads

Claude Opus 4.7: 46.1 (#24), DeepSeek-V3.1-Terminus: 43.5 (#88)

BenchmarkClaude Opus 4.7DeepSeek-V3.1-Terminus
LMArena Longer Query15051426

Writing & Preference Claude Opus 4.7 leads

Claude Opus 4.7: 75.3 (#8), DeepSeek-V3.1-Terminus: 61.3 (#87)

BenchmarkClaude Opus 4.7DeepSeek-V3.1-Terminus
LMArena Text14911420
LMArena Creative Writing14861404
LMArena Multi-Turn15061411
EQ-Bench Creative Writing1914—
EQ-Bench 41311—

Frequently asked questions

Is Claude Opus 4.7 better than DeepSeek-V3.1-Terminus?

Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 42.6 on the Noometry Index. DeepSeek-V3.1-Terminus costs 21× 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 DeepSeek-V3.1-Terminus?

DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; Claude Opus 4.7 lists at $5 and $25.

Is Claude Opus 4.7 or DeepSeek-V3.1-Terminus better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.9 versus 41.5 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.7 does, with 1M tokens against 164K.

How many benchmarks do Claude Opus 4.7 and DeepSeek-V3.1-Terminus share?

16 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and DeepSeek-V3.1-Terminus has 16.

Related comparisons

Go deeper