Model comparison
Claude 3.5 Haiku vs DeepSeek LLM 67B
Claude 3.5 Haiku is the stronger model overall, scoring 29.2 to 24.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeekSummary
- They share 14 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 8 categories and DeepSeek LLM 67B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude 3.5 Haiku leads 18.7 to 7.0.
- The biggest single-benchmark swing is MATH Level 5: 46.4% for Claude 3.5 Haiku and 6.4% for DeepSeek LLM 67B.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Haiku | DeepSeek LLM 67B | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 29.2 | 24.9 |
| Released | 2024-10-22 | 2023-11-29 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 49 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Haiku leads
Claude 3.5 Haiku: 32.9 (#265), DeepSeek LLM 67B: 31.9 (#278)
| Benchmark | Claude 3.5 Haiku | DeepSeek LLM 67B |
|---|---|---|
| LMArena Coding | 1286 | 1096 |
| Aider Polyglot | 28% | — |
| SciCode | 27.4% | — |
| WeirdML | 30.7% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Haiku: 28.0 (#95), DeepSeek LLM 67B: —
| Benchmark | Claude 3.5 Haiku | DeepSeek LLM 67B |
|---|---|---|
| BALROG | 19.3% | — |
Reasoning Claude 3.5 Haiku leads
Claude 3.5 Haiku: 17.7 (#290), DeepSeek LLM 67B: 16.5 (#304)
| Benchmark | Claude 3.5 Haiku | DeepSeek LLM 67B |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1070 |
| Epoch Capabilities Index | 127.15 | 110.5 |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 56.7% | — |
| LiveBench Data Analysis | 48.5% | — |
| LiveBench | 43.5% | — |
Math Claude 3.5 Haiku leads
Claude 3.5 Haiku: 14.7 (#300), DeepSeek LLM 67B: 8.7 (#324)
| Benchmark | Claude 3.5 Haiku | DeepSeek LLM 67B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 0.8% |
| LMArena Math | 1244 | 1108 |
| MATH Level 5 | 46.4% | 6.4% |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Claude 3.5 Haiku leads
Claude 3.5 Haiku: 18.7 (#281), DeepSeek LLM 67B: 7.0 (#313)
| Benchmark | Claude 3.5 Haiku | DeepSeek LLM 67B |
|---|---|---|
| GPQA Diamond | 38.1% | 24.6% |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| GPQA (HELM) | 36.3% | — |
| LMArena Expert | 1208 | — |
| MMLU | 74.3% | — |
Multimodal Not comparable
Claude 3.5 Haiku: 26.8 (#117), DeepSeek LLM 67B: —
| Benchmark | Claude 3.5 Haiku | DeepSeek LLM 67B |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
Multilingual Claude 3.5 Haiku leads
Claude 3.5 Haiku: 40.0 (#218), DeepSeek LLM 67B: 29.4 (#267)
| Benchmark | Claude 3.5 Haiku | DeepSeek LLM 67B |
|---|---|---|
| LMArena Non-English | 1238 | 1073 |
| LMArena Chinese | 1229 | 1132 |
| LMArena French | 1264 | — |
| LMArena German | 1237 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1173 | — |
| LMArena Russian | 1253 | — |
| LMArena Spanish | 1261 | — |
Instruction Following Claude 3.5 Haiku leads
Claude 3.5 Haiku: 62.9 (#234), DeepSeek LLM 67B: 55.4 (#277)
| Benchmark | Claude 3.5 Haiku | DeepSeek LLM 67B |
|---|---|---|
| LMArena Instruction Following | 1241 | 1079 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
Long Context Claude 3.5 Haiku leads
Claude 3.5 Haiku: 38.3 (#200), DeepSeek LLM 67B: 33.1 (#265)
| Benchmark | Claude 3.5 Haiku | DeepSeek LLM 67B |
|---|---|---|
| LMArena Longer Query | 1261 | 1092 |
Writing & Preference Claude 3.5 Haiku leads
Claude 3.5 Haiku: 42.7 (#234), DeepSeek LLM 67B: 31.6 (#282)
| Benchmark | Claude 3.5 Haiku | DeepSeek LLM 67B |
|---|---|---|
| LMArena Text | 1255 | 1105 |
| LMArena Creative Writing | 1233 | 1067 |
| LMArena Multi-Turn | 1265 | 1082 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | 1146 | — |
| WildBench | 76% | — |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than DeepSeek LLM 67B?
Claude 3.5 Haiku is the stronger model overall, scoring 29.2 to 24.9 on the Noometry Index.
Is Claude 3.5 Haiku or DeepSeek LLM 67B better for coding?
Claude 3.5 Haiku scores higher on coding benchmarks: 32.9 versus 31.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and DeepSeek LLM 67B share?
14 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and DeepSeek LLM 67B has 15.