# Claude Sonnet 5.5 vs DeepSeek-V3.2-Exp

> Claude Sonnet 5.5 is the stronger model overall, scoring 60.5 to 44.9 on the Noometry Index. DeepSeek-V3.2-Exp costs 14× less per token, which makes it the better buy when Claude Sonnet 5.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-5-vs-deepseek-v3-2-exp
- Last updated: 2026-10-10
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. Claude Sonnet 5.5 scores higher in 5 categories and DeepSeek-V3.2-Exp in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5.5 leads 88.7 to 40.8.
- The biggest single-benchmark swing is ProofBench: 100% for Claude Sonnet 5.5 and 8% for DeepSeek-V3.2-Exp.
- DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 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-V3.2-Exp has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 60.5 | 44.9 |
| Rank | 10 | 68 |
| Context | 1M | 164K |
| Input $/M | $2 | $0.26 |
| Output $/M | $10 | $0.38 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 5.5: 65.5 (#6)
- DeepSeek-V3.2-Exp: 46.4 (#61)

| Benchmark | Claude Sonnet 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena WebDev | 1699 | 1362 |
| SciCode | 61% | 38.9% |
| FrontierCode | 52.1% | — |
| SWE-bench Verified (bash only) | — | 70% |
| Aider Polyglot | — | 74.2% |
| CursorBench | 55.5% | — |
| SWE-bench Multilingual | — | 59% |
| FrontierSWE | 61.9% | — |
| WeirdML | — | 39.5% |
| LMArena Coding | — | 1454 |
| ALE-Bench | 1,819 | — |

## Agentic & Tool Use

- Claude Sonnet 5.5: 44.9 (#14)
- DeepSeek-V3.2-Exp: 37.9 (#31)

| Benchmark | Claude Sonnet 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| Terminal-Bench | — | 39.6% |
| APEX-Agents | 75.5% | — |
| Berkeley Function Calling Leaderboard | — | 56.7% |
| TheAgentCompany | — | 42.9% |
| Vending-Bench 2 | — | 1,034 |

## Reasoning

- Claude Sonnet 5.5: 52.4 (#29)
- DeepSeek-V3.2-Exp: 22.0 (#185)

| Benchmark | Claude Sonnet 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| CritPt | 31.4% | 2.9% |
| ARC-AGI-2 | — | 4% |
| Kagi LLM Benchmark | — | 52.2% |
| NYT Connections (extended) | — | 36.7% |
| ARC-AGI-1 | — | 57% |
| Chess Puzzles | — | 14% |
| Thematic Generalization | — | 65% |
| LMArena Hard Prompts | — | 1433 |
| Mystery Game Puzzles | 65% | — |
| DTBench | — | 87.7% |
| LMCA | — | 29.1% |
| Epoch Capabilities Index | — | 146.28 |

## Math

- Claude Sonnet 5.5: 88.7 (#4)
- DeepSeek-V3.2-Exp: 40.8 (#75)

| Benchmark | Claude Sonnet 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 87.8% |
| ProofBench | 100% | 8% |
| FrontierMath (Tiers 1-3) | 88.8% | — |
| FrontierMath Tier 4 | 80.5% | — |
| MathArena Final-Answer Competitions | — | 57.7% |
| LMArena Math | — | 1435 |
| FrontierMath (Feb 2025 set) | — | 22.1% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Claude Sonnet 5.5: 66.0 (#11)
- DeepSeek-V3.2-Exp: 51.6 (#61)

| Benchmark | Claude Sonnet 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| GPQA Diamond | 95.6% | 83.4% |
| SimpleQA Verified | 46.5% | — |
| Vectara Hallucination Rate | — | 5.3% |
| LMArena Expert | — | 1436 |

## Multimodal

- Claude Sonnet 5.5: 53.2 (#5)
- DeepSeek-V3.2-Exp: —

| Benchmark | Claude Sonnet 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| Furniture Assembly | 75% | — |

## Multilingual

- Claude Sonnet 5.5: —
- DeepSeek-V3.2-Exp: 52.4 (#85)

| Benchmark | Claude Sonnet 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Non-English | — | 1409 |
| LMArena Chinese | — | 1461 |
| LMArena French | — | 1435 |
| LMArena German | — | 1440 |
| LMArena Japanese | — | 1377 |
| LMArena Korean | — | 1372 |
| LMArena Russian | — | 1423 |
| LMArena Spanish | — | 1441 |

## Instruction Following

- Claude Sonnet 5.5: —
- DeepSeek-V3.2-Exp: 74.7 (#89)

| Benchmark | Claude Sonnet 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Instruction Following | — | 1413 |

## Long Context

- Claude Sonnet 5.5: —
- DeepSeek-V3.2-Exp: 47.6 (#15)

| Benchmark | Claude Sonnet 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| Fiction.LiveBench | — | 83.3% |
| CL-bench | — | 13.2% |
| CL-bench Life | — | 9.5% |
| LMArena Longer Query | — | 1428 |

## Writing & Preference

- Claude Sonnet 5.5: —
- DeepSeek-V3.2-Exp: 62.5 (#73)

| Benchmark | Claude Sonnet 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Text | — | 1425 |
| LMArena Creative Writing | — | 1403 |
| EQ-Bench Creative Writing | — | 1515 |
| LMArena Multi-Turn | — | 1427 |

## FAQ

### Is Claude Sonnet 5.5 better than DeepSeek-V3.2-Exp?

Claude Sonnet 5.5 is the stronger model overall, scoring 60.5 to 44.9 on the Noometry Index. DeepSeek-V3.2-Exp costs 14× less per token, which makes it the better buy when Claude Sonnet 5.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 5.5 or DeepSeek-V3.2-Exp?

DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; Claude Sonnet 5.5 lists at $2 and $10.

### Is Claude Sonnet 5.5 or DeepSeek-V3.2-Exp better for coding?

Claude Sonnet 5.5 scores higher on coding benchmarks: 65.5 versus 46.4 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-V3.2-Exp share?

6 benchmarks have published results for both models. Claude Sonnet 5.5 has 16 scored results on Noometry and DeepSeek-V3.2-Exp has 48.