Model comparison
Claude 3 Haiku vs Llama 13b
Claude 3 Haiku is the stronger model overall, scoring 25.9 to 24.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
MetaSummary
- They share 12 benchmarks with published results for both. Claude 3 Haiku scores higher in 5 categories and Llama 13b in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Claude 3 Haiku leads 61.3 to 36.7.
- Llama 13b has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | Llama 13b | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 25.9 | 24.4 |
| Released | 2024-03-07 | 2023-02-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3 Haiku leads
Claude 3 Haiku: 26.4 (#325), Llama 13b: 21.4 (#337)
| Benchmark | Claude 3 Haiku | Llama 13b |
|---|---|---|
| LMArena Coding | 1199 | 683 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Claude 3 Haiku leads
Claude 3 Haiku: 16.3 (#307), Llama 13b: 14.0 (#329)
| Benchmark | Claude 3 Haiku | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1174 | 728 |
| Epoch Capabilities Index | 118.35 | 100.58 |
| WinoGrande | 74.2% | 73% |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| BIG-Bench Hard | — | 37.9% |
| ForecastBench | 53.2 | — |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
Math Llama 13b leads
Claude 3 Haiku: 9.8 (#319), Llama 13b: 26.7 (#256)
| Benchmark | Claude 3 Haiku | Llama 13b |
|---|---|---|
| LMArena Math | 1188 | 838 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
| GSM8K | — | 20.6% |
Knowledge Not comparable
Claude 3 Haiku: 17.3 (#285), Llama 13b: —
| Benchmark | Claude 3 Haiku | Llama 13b |
|---|---|---|
| MMLU | 73.8% | 47.7% |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| LMArena Expert | 1148 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Llama 13b: —
| Benchmark | Claude 3 Haiku | Llama 13b |
|---|---|---|
| ScienceQA | 72% | 43.3% |
| LMArena Vision | 950 | — |
Multilingual Claude 3 Haiku leads
Claude 3 Haiku: 36.0 (#243), Llama 13b: 16.6 (#297)
| Benchmark | Claude 3 Haiku | Llama 13b |
|---|---|---|
| LMArena Non-English | 1178 | 819 |
| 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), Llama 13b: 36.7 (#305)
| Benchmark | Claude 3 Haiku | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1173 | 781 |
Long Context Not comparable
Claude 3 Haiku: 36.1 (#237), Llama 13b: —
| Benchmark | Claude 3 Haiku | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1190 | — |
Writing & Preference Claude 3 Haiku leads
Claude 3 Haiku: 29.7 (#291), Llama 13b: 13.8 (#312)
| Benchmark | Claude 3 Haiku | Llama 13b |
|---|---|---|
| LMArena Text | 1195 | 834 |
| LMArena Creative Writing | 1157 | 794 |
| LMArena Multi-Turn | 1190 | 753 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Llama 13b?
Claude 3 Haiku is the stronger model overall, scoring 25.9 to 24.4 on the Noometry Index.
Is Claude 3 Haiku or Llama 13b better for coding?
Claude 3 Haiku scores higher on coding benchmarks: 26.4 versus 21.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Llama 13b share?
12 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Llama 13b has 21.