# Claude Opus 4.8 vs DeepSeek LLM 67B

> Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-opus-4-8-vs-deepseek-llm-67b
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Claude Opus 4.8 scores higher in 8 categories and DeepSeek LLM 67B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4.8 leads 78.4 to 8.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for Claude Opus 4.8 and 0.8% for DeepSeek LLM 67B.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Opus 4.8 | DeepSeek LLM 67B |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 60.7 | 24.9 |
| Rank | 13 | 347 |
| Context | 1M | — |
| Input $/M | $5 | — |
| Output $/M | $25 | — |
| Weights | Proprietary | Open |

## Coding

- Claude Opus 4.8: 59.9 (#12)
- DeepSeek LLM 67B: 31.9 (#278)

| Benchmark | Claude Opus 4.8 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Coding | 1490 | 1096 |
| DeepSWE | 59% | — |
| FrontierCode | 46.5% | — |
| LMArena WebDev | 1556 | — |
| SciCode | 53.5% | — |
| GSO | 47.1% | — |
| WeirdML | 82.9% | — |
| ALE-Bench | 1,564 | — |

## Agentic & Tool Use

- Claude Opus 4.8: 47.6 (#11)
- DeepSeek LLM 67B: —

| Benchmark | Claude Opus 4.8 | DeepSeek LLM 67B |
|---|---|---|
| APEX-Agents | 48.9% | — |
| OSWorld 2.0 | 20.6% | — |
| Remote Labor Index | 8.3% | — |
| τ²-bench Banking | 39.7% | — |
| DeepResearch Bench | 50.2% | — |
| PostTrainBench | 33.8% | — |
| GBAEval | 70.9% | — |
| GDP.pdf | 24% | — |
| LMArena Search | 1204 | — |
| Vending-Bench 2 | 5,787 | — |

## Reasoning

- Claude Opus 4.8: 64.7 (#16)
- DeepSeek LLM 67B: 16.5 (#304)

| Benchmark | Claude Opus 4.8 | DeepSeek LLM 67B |
|---|---|---|
| Chess Puzzles | 34% | 0% |
| LMArena Hard Prompts | 1482 | 1070 |
| Epoch Capabilities Index | 158.21 | 110.5 |
| ARC-AGI-2 | 72.1% | — |
| SimpleBench | 64.8% | — |
| Kagi LLM Benchmark | 88.8% | — |
| NYT Connections (extended) | 91.1% | — |
| ARC-AGI-1 | 92.5% | — |
| CritPt | 20.9% | — |
| EnigmaEval | 23.5% | — |
| EBR-Bench | 28.6% | — |
| Mystery Game Puzzles | 36% | — |
| DTBench | 94.9% | — |
| LMCA | 57.5% | — |
| Surface Evolver Bench | 87.5% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 59.9 | — |

## Math

- Claude Opus 4.8: 78.4 (#13)
- DeepSeek LLM 67B: 8.7 (#324)

| Benchmark | Claude Opus 4.8 | DeepSeek LLM 67B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | 0.8% |
| LMArena Math | 1487 | 1108 |
| FrontierMath (Tiers 1-3) | 80% | — |
| FrontierMath Tier 4 | 56.1% | — |
| MathArena Final-Answer Competitions | 91.8% | — |
| ProofBench | 69% | — |
| MATH Level 5 | — | 6.4% |
| FrontierMath (Feb 2025 set) | 47.2% | — |
| FrontierMath Tier 4 (v1) | 31.3% | — |

## Knowledge

- Claude Opus 4.8: 61.3 (#29)
- DeepSeek LLM 67B: 7.0 (#313)

| Benchmark | Claude Opus 4.8 | DeepSeek LLM 67B |
|---|---|---|
| GPQA Diamond | 91% | 24.6% |
| SimpleQA Verified | 53% | — |
| LMArena Expert | 1502 | — |

## Multimodal

- Claude Opus 4.8: 42.9 (#26)
- DeepSeek LLM 67B: —

| Benchmark | Claude Opus 4.8 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Vision | 1294 | — |
| Blueprint-Bench 2 | 14.5% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1475 | — |

## Multilingual

- Claude Opus 4.8: 55.2 (#33)
- DeepSeek LLM 67B: 29.4 (#267)

| Benchmark | Claude Opus 4.8 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Non-English | 1450 | 1073 |
| LMArena Chinese | 1507 | 1132 |
| LMArena French | 1481 | — |
| LMArena German | 1472 | — |
| LMArena Japanese | 1440 | — |
| LMArena Korean | 1432 | — |
| LMArena Russian | 1474 | — |
| LMArena Spanish | 1466 | — |

## Instruction Following

- Claude Opus 4.8: 77.4 (#24)
- DeepSeek LLM 67B: 55.4 (#277)

| Benchmark | Claude Opus 4.8 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Instruction Following | 1476 | 1079 |

## Long Context

- Claude Opus 4.8: 45.4 (#35)
- DeepSeek LLM 67B: 33.1 (#265)

| Benchmark | Claude Opus 4.8 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Longer Query | 1483 | 1092 |

## Writing & Preference

- Claude Opus 4.8: 72.0 (#16)
- DeepSeek LLM 67B: 31.6 (#282)

| Benchmark | Claude Opus 4.8 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Text | 1461 | 1105 |
| LMArena Creative Writing | 1454 | 1067 |
| LMArena Multi-Turn | 1476 | 1082 |
| EQ-Bench Creative Writing | 1840 | — |
| EQ-Bench 4 | 1281 | — |

## FAQ

### Is Claude Opus 4.8 better than DeepSeek LLM 67B?

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 24.9 on the Noometry Index.

### Is Claude Opus 4.8 or DeepSeek LLM 67B better for coding?

Claude Opus 4.8 scores higher on coding benchmarks: 59.9 versus 31.9 in the Noometry coding category.

### How many benchmarks do Claude Opus 4.8 and DeepSeek LLM 67B share?

14 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and DeepSeek LLM 67B has 15.