Model comparison
Claude 3 Haiku vs Llama2 70b Steerlm Chat
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 25.9 on the Noometry Index.
Last verified . 9 shared benchmarks.
NVIDIASummary
- They share 9 benchmarks with published results for both. Claude 3 Haiku scores higher in 3 categories and Llama2 70b Steerlm Chat in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama2 70b Steerlm Chat leads 31.3 to 9.8.
- Llama2 70b Steerlm Chat has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | Anthropic | NVIDIA |
| Noometry Index | 25.9 | 31.8 |
| Released | 2024-03-07 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama2 70b Steerlm Chat leads
Claude 3 Haiku: 26.4 (#325), Llama2 70b Steerlm Chat: 29.9 (#300)
| Benchmark | Claude 3 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1199 | 1025 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Llama2 70b Steerlm Chat leads
Claude 3 Haiku: 16.3 (#307), Llama2 70b Steerlm Chat: 20.0 (#246)
| Benchmark | Claude 3 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1047 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Llama2 70b Steerlm Chat leads
Claude 3 Haiku: 9.8 (#319), Llama2 70b Steerlm Chat: 31.3 (#226)
| Benchmark | Claude 3 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1188 | 1072 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
Knowledge Not comparable
Claude 3 Haiku: 17.3 (#285), Llama2 70b Steerlm Chat: —
| Benchmark | Claude 3 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| LMArena Expert | 1148 | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Llama2 70b Steerlm Chat: —
| Benchmark | Claude 3 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Claude 3 Haiku leads
Claude 3 Haiku: 36.0 (#243), Llama2 70b Steerlm Chat: 28.8 (#270)
| Benchmark | Claude 3 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 1178 | 1063 |
| LMArena Chinese | 1155 | — |
| LMArena French | 1195 | — |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1109 | — |
| LMArena Russian | 1204 | — |
| LMArena Spanish | 1166 | — |
Instruction Following Claude 3 Haiku leads
Claude 3 Haiku: 61.3 (#247), Llama2 70b Steerlm Chat: 54.2 (#279)
| Benchmark | Claude 3 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1173 | 1060 |
Long Context Claude 3 Haiku leads
Claude 3 Haiku: 36.1 (#237), Llama2 70b Steerlm Chat: 30.4 (#288)
| Benchmark | Claude 3 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 1190 | 998 |
Writing & Preference Llama2 70b Steerlm Chat leads
Claude 3 Haiku: 29.7 (#291), Llama2 70b Steerlm Chat: 31.6 (#283)
| Benchmark | Claude 3 Haiku | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1195 | 1098 |
| LMArena Creative Writing | 1157 | 1091 |
| LMArena Multi-Turn | 1190 | 1058 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Llama2 70b Steerlm Chat?
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Llama2 70b Steerlm Chat better for coding?
Llama2 70b Steerlm Chat scores higher on coding benchmarks: 29.9 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Llama2 70b Steerlm Chat has 9.