# Claude 2.1 vs DeepSeek-V3.1-Terminus

> DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-1-vs-deepseek-v3-1-terminus
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Claude 2.1 scores higher in 0 categories and DeepSeek-V3.1-Terminus in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1-Terminus leads 35.7 to 9.6.
- The biggest single-benchmark swing is DTBench: 51% for Claude 2.1 and 81.3% for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 2.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 24.9 | 42.6 |
| Rank | 340 | 96 |
| Context | — | 164K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1 |
| Weights | Proprietary | Open |

## Coding

- Claude 2.1: 25.8 (#322)
- DeepSeek-V3.1-Terminus: 41.5 (#114)

| Benchmark | Claude 2.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| SciCode | — | 40.6% |
| WeirdML | 7.1% | — |
| LMArena Coding | — | 1426 |
| ALE-Bench | — | 745.17 |

## Reasoning

- Claude 2.1: 20.6 (#216)
- DeepSeek-V3.1-Terminus: 25.7 (#126)

| Benchmark | Claude 2.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| DTBench | 51% | 81.3% |
| Kagi LLM Benchmark | — | 57.4% |
| CritPt | — | 1.7% |
| LMArena Hard Prompts | — | 1427 |
| LMCA | — | 28.6% |
| Epoch Capabilities Index | 119.22 | — |
| ForecastBench | 54.2 | — |

## Math

- Claude 2.1: 9.6 (#309)
- DeepSeek-V3.1-Terminus: 35.7 (#138)

| Benchmark | Claude 2.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| LMArena Math | — | 1402 |

## Knowledge

- Claude 2.1: 15.5 (#287)
- DeepSeek-V3.1-Terminus: —

| Benchmark | Claude 2.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| GPQA Diamond | 33% | — |
| MMLU | 73.5% | — |

## Multilingual

- Claude 2.1: —
- DeepSeek-V3.1-Terminus: 52.3 (#87)

| Benchmark | Claude 2.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Non-English | — | 1407 |
| LMArena Russian | — | 1434 |

## Instruction Following

- Claude 2.1: —
- DeepSeek-V3.1-Terminus: 74.4 (#96)

| Benchmark | Claude 2.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Instruction Following | — | 1406 |

## Long Context

- Claude 2.1: —
- DeepSeek-V3.1-Terminus: 43.5 (#88)

| Benchmark | Claude 2.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Longer Query | — | 1426 |

## Writing & Preference

- Claude 2.1: —
- DeepSeek-V3.1-Terminus: 61.3 (#87)

| Benchmark | Claude 2.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Text | — | 1420 |
| LMArena Creative Writing | — | 1404 |
| LMArena Multi-Turn | — | 1411 |

## FAQ

### Is Claude 2.1 better than DeepSeek-V3.1-Terminus?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 24.9 on the Noometry Index.

### Is Claude 2.1 or DeepSeek-V3.1-Terminus better for coding?

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 25.8 in the Noometry coding category.

### How many benchmarks do Claude 2.1 and DeepSeek-V3.1-Terminus share?

1 benchmark has published results for both models. Claude 2.1 has 7 scored results on Noometry and DeepSeek-V3.1-Terminus has 16.