Model comparison
Claude 3.5 Haiku vs Granite 3.1 2b Instruct
Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 29.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 4 categories and Granite 3.1 2b Instruct in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Granite 3.1 2b Instruct leads 33.1 to 14.7.
- Granite 3.1 2b Instruct has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Haiku | Granite 3.1 2b Instruct | |
|---|---|---|
| Provider | Anthropic | IBM |
| Noometry Index | 29.2 | 33.2 |
| Released | 2024-10-22 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 49 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3.5 Haiku: 32.9 (#265), Granite 3.1 2b Instruct: 33.4 (#257)
| Benchmark | Claude 3.5 Haiku | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Coding | 1286 | 1149 |
| 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), Granite 3.1 2b Instruct: —
| Benchmark | Claude 3.5 Haiku | Granite 3.1 2b Instruct |
|---|---|---|
| BALROG | 19.3% | — |
Reasoning Granite 3.1 2b Instruct leads
Claude 3.5 Haiku: 17.7 (#290), Granite 3.1 2b Instruct: 22.0 (#209)
| Benchmark | Claude 3.5 Haiku | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1138 |
| CritPt | 0% | — |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 56.7% | — |
| LiveBench Data Analysis | 48.5% | — |
| Epoch Capabilities Index | 127.15 | — |
| LiveBench | 43.5% | — |
Math Granite 3.1 2b Instruct leads
Claude 3.5 Haiku: 14.7 (#300), Granite 3.1 2b Instruct: 33.1 (#206)
| Benchmark | Claude 3.5 Haiku | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Math | 1244 | 1159 |
| 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 Granite 3.1 2b Instruct leads
Claude 3.5 Haiku: 18.7 (#281), Granite 3.1 2b Instruct: 30.8 (#224)
| Benchmark | Claude 3.5 Haiku | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Expert | 1208 | 1131 |
| GPQA Diamond | 38.1% | — |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |
Multimodal Not comparable
Claude 3.5 Haiku: 26.8 (#117), Granite 3.1 2b Instruct: —
| Benchmark | Claude 3.5 Haiku | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
Multilingual Claude 3.5 Haiku leads
Claude 3.5 Haiku: 40.0 (#218), Granite 3.1 2b Instruct: 29.1 (#269)
| Benchmark | Claude 3.5 Haiku | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Non-English | 1238 | 1068 |
| LMArena Chinese | 1229 | 1139 |
| LMArena Russian | 1253 | 1063 |
| LMArena French | 1264 | — |
| LMArena German | 1237 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1173 | — |
| LMArena Spanish | 1261 | — |
Instruction Following Claude 3.5 Haiku leads
Claude 3.5 Haiku: 62.9 (#234), Granite 3.1 2b Instruct: 57.7 (#264)
| Benchmark | Claude 3.5 Haiku | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Instruction Following | 1241 | 1116 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
Long Context Claude 3.5 Haiku leads
Claude 3.5 Haiku: 38.3 (#200), Granite 3.1 2b Instruct: 35.0 (#244)
| Benchmark | Claude 3.5 Haiku | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Longer Query | 1261 | 1155 |
Writing & Preference Claude 3.5 Haiku leads
Claude 3.5 Haiku: 42.7 (#234), Granite 3.1 2b Instruct: 34.1 (#274)
| Benchmark | Claude 3.5 Haiku | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Text | 1255 | 1127 |
| LMArena Creative Writing | 1233 | 1116 |
| LMArena Multi-Turn | 1265 | 1099 |
| 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 Granite 3.1 2b Instruct?
Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or Granite 3.1 2b Instruct better for coding?
They score almost the same on coding (32.9 vs 33.4); test both on your own repository before choosing.
How many benchmarks do Claude 3.5 Haiku and Granite 3.1 2b Instruct share?
12 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Granite 3.1 2b Instruct has 12.