Model comparison

Claude Sonnet 5.5 vs DeepSeek-V3.1-Terminus

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 8.8× less per token, which makes it the better buy when Claude Sonnet 5.5's lead doesn't matter for your workload.

Last verified October 12, 2026. 13 shared benchmarks.

Claude Sonnet 5.5 Anthropic

61.9

Rank #10 Confirmed

DeepSeek-V3.1-Terminus

DeepSeek

43.1

Rank #97 Confirmed

Summary

They share 13 benchmarks with published results for both. Claude Sonnet 5.5 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 Sonnet 5.5 leads 87.9 to 38.5.
The biggest single-benchmark swing is CritPt: 31.4% for Claude Sonnet 5.5 and 1.7% for DeepSeek-V3.1-Terminus.
DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.5.
Claude Sonnet 5.5 accepts more context: 1M tokens versus 164K.
DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 5.5 and DeepSeek-V3.1-Terminus specifications
	Claude Sonnet 5.5	DeepSeek-V3.1-Terminus
Provider	Anthropic	DeepSeek
Noometry Index	61.9	43.1
Released	2026-09-28	2025-09-22
Weights	Proprietary	Open
Context window	1M	164K
Max output	128K	147K
Input $ / M tokens	$2	$0.27
Output $ / M tokens	$10	$1
Results tracked	32	16

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

Category by category

Coding Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 67.3 (#6), DeepSeek-V3.1-Terminus: 42.0 (#113)

Coding benchmarks
Benchmark	Claude Sonnet 5.5	DeepSeek-V3.1-Terminus
SciCode	61%	40.6%
LMArena Coding	1513	1426
ALE-Bench	1,819	745.17
FrontierCode	52.1%	—
CursorBench	55.5%	—
LMArena WebDev	1774	—
FrontierSWE	61.9%	—

Agentic & Tool Use Not comparable

Claude Sonnet 5.5: 45.0 (#16), DeepSeek-V3.1-Terminus: —

Agentic & Tool Use benchmarks
Benchmark	Claude Sonnet 5.5	DeepSeek-V3.1-Terminus
APEX-Agents	75.5%	—

Reasoning Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 54.0 (#28), DeepSeek-V3.1-Terminus: 26.4 (#133)

Reasoning benchmarks
Benchmark	Claude Sonnet 5.5	DeepSeek-V3.1-Terminus
CritPt	31.4%	1.7%
LMArena Hard Prompts	1495	1426
Kagi LLM Benchmark	—	57.4%
NYT Connections (extended)	80.5%	—
Mystery Game Puzzles	65%	—
DTBench	—	81.3%
LMCA	—	28.6%
Epoch Capabilities Index	165.03	—

Math Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 87.9 (#6), DeepSeek-V3.1-Terminus: 38.5 (#137)

Math benchmarks
Benchmark	Claude Sonnet 5.5	DeepSeek-V3.1-Terminus
LMArena Math	1510	1402
FrontierMath (Tiers 1-3)	88.8%	—
FrontierMath Tier 4	80.5%	—
OTIS Mock AIME 2024-2025	100%	—
ProofBench	100%	—
FrontierMath Erdős	2.9%	—

Knowledge Not comparable

Claude Sonnet 5.5: 66.0 (#12), DeepSeek-V3.1-Terminus: —

Knowledge benchmarks
Benchmark	Claude Sonnet 5.5	DeepSeek-V3.1-Terminus
GPQA Diamond	95.6%	—
SimpleQA Verified	46.5%	—
LMArena Expert	1540	—

Multimodal Not comparable

Claude Sonnet 5.5: 51.5 (#6), DeepSeek-V3.1-Terminus: —

Multimodal benchmarks
Benchmark	Claude Sonnet 5.5	DeepSeek-V3.1-Terminus
LMArena Vision	1289	—
Furniture Assembly	75%	—

Multilingual Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 55.3 (#30), DeepSeek-V3.1-Terminus: 52.1 (#92)

Multilingual benchmarks
Benchmark	Claude Sonnet 5.5	DeepSeek-V3.1-Terminus
LMArena Non-English	1452	1407
LMArena Russian	1451	1436
LMArena Chinese	1522	—

Instruction Following Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 78.3 (#11), DeepSeek-V3.1-Terminus: 74.0 (#106)

Instruction Following benchmarks
Benchmark	Claude Sonnet 5.5	DeepSeek-V3.1-Terminus
LMArena Instruction Following	1495	1404

Long Context Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 45.9 (#28), DeepSeek-V3.1-Terminus: 43.4 (#97)

Long Context benchmarks
Benchmark	Claude Sonnet 5.5	DeepSeek-V3.1-Terminus
LMArena Longer Query	1498	1421

Writing & Preference Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 66.0 (#40), DeepSeek-V3.1-Terminus: 61.0 (#92)

Writing & Preference benchmarks
Benchmark	Claude Sonnet 5.5	DeepSeek-V3.1-Terminus
LMArena Text	1471	1419
LMArena Creative Writing	1465	1403
LMArena Multi-Turn	1474	1411

Frequently asked questions

Is Claude Sonnet 5.5 better than DeepSeek-V3.1-Terminus?

Which is cheaper, Claude Sonnet 5.5 or DeepSeek-V3.1-Terminus?

DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; Claude Sonnet 5.5 lists at $2 and $10.

Is Claude Sonnet 5.5 or DeepSeek-V3.1-Terminus better for coding?

Claude Sonnet 5.5 scores higher on coding benchmarks: 67.3 versus 42.0 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 5.5 does, with 1M tokens against 164K.

How many benchmarks do Claude Sonnet 5.5 and DeepSeek-V3.1-Terminus share?

13 benchmarks have published results for both models. Claude Sonnet 5.5 has 32 scored results on Noometry and DeepSeek-V3.1-Terminus has 16.