Model comparison
Claude 3.5 Haiku vs Llama2 70b Steerlm Chat
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 29.2 on the Noometry Index.
Last verified . 9 shared benchmarks.
NVIDIASummary
- They share 9 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 5 categories and Llama2 70b Steerlm Chat in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama2 70b Steerlm Chat leads 31.3 to 14.7.
- Llama2 70b Steerlm Chat has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Haiku | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | Anthropic | NVIDIA |
| Noometry Index | 29.2 | 31.8 |
| Released | 2024-10-22 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 49 | 9 |
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), Llama2 70b Steerlm Chat: 29.9 (#300)
| Benchmark | Claude 3.5 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1286 | 1025 |
| 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), Llama2 70b Steerlm Chat: —
| Benchmark | Claude 3.5 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| BALROG | 19.3% | — |
Reasoning Llama2 70b Steerlm Chat leads
Claude 3.5 Haiku: 17.7 (#290), Llama2 70b Steerlm Chat: 20.0 (#246)
| Benchmark | Claude 3.5 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1047 |
| CritPt | 0% | — |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 56.7% | — |
| LiveBench Data Analysis | 48.5% | — |
| Epoch Capabilities Index | 127.15 | — |
| LiveBench | 43.5% | — |
Math Llama2 70b Steerlm Chat leads
Claude 3.5 Haiku: 14.7 (#300), Llama2 70b Steerlm Chat: 31.3 (#226)
| Benchmark | Claude 3.5 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1244 | 1072 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Not comparable
Claude 3.5 Haiku: 18.7 (#281), Llama2 70b Steerlm Chat: —
| Benchmark | Claude 3.5 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| GPQA Diamond | 38.1% | — |
| 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), Llama2 70b Steerlm Chat: —
| Benchmark | Claude 3.5 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
Multilingual Claude 3.5 Haiku leads
Claude 3.5 Haiku: 40.0 (#218), Llama2 70b Steerlm Chat: 28.8 (#270)
| Benchmark | Claude 3.5 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 1238 | 1063 |
| LMArena Chinese | 1229 | — |
| 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), Llama2 70b Steerlm Chat: 54.2 (#279)
| Benchmark | Claude 3.5 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1241 | 1060 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
Long Context Claude 3.5 Haiku leads
Claude 3.5 Haiku: 38.3 (#200), Llama2 70b Steerlm Chat: 30.4 (#288)
| Benchmark | Claude 3.5 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 1261 | 998 |
Writing & Preference Claude 3.5 Haiku leads
Claude 3.5 Haiku: 42.7 (#234), Llama2 70b Steerlm Chat: 31.6 (#283)
| Benchmark | Claude 3.5 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1255 | 1098 |
| LMArena Creative Writing | 1233 | 1091 |
| LMArena Multi-Turn | 1265 | 1058 |
| 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 Llama2 70b Steerlm Chat?
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or Llama2 70b Steerlm Chat better for coding?
Claude 3.5 Haiku scores higher on coding benchmarks: 32.9 versus 29.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Llama2 70b Steerlm Chat has 9.