Model comparison
Claude 3.5 Haiku vs Granite 4.0 Micro
Claude 3.5 Haiku and Granite 4.0 Micro score almost the same on the Noometry Index (29.2 vs 29.0), so choose on price, context window or the category you care about most.
Last verified . 7 shared benchmarks.
Summary
- They share 7 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 2 categories and Granite 4.0 Micro in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude 3.5 Haiku leads 18.7 to 9.9.
- The biggest single-benchmark swing is MMLU-Pro: 60.5% for Claude 3.5 Haiku and 39.5% for Granite 4.0 Micro.
- Granite 4.0 Micro has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Haiku | Granite 4.0 Micro | |
|---|---|---|
| Provider | Anthropic | IBM |
| Noometry Index | 29.2 | 29.0 |
| Released | 2024-10-22 | 2025-10-02 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 118K |
| Input $ / M tokens | — | $0.017 |
| Output $ / M tokens | — | $0.11 |
| Results tracked | 49 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 3.5 Haiku: 32.9 (#265), Granite 4.0 Micro: —
| Benchmark | Claude 3.5 Haiku | Granite 4.0 Micro |
|---|---|---|
| Aider Polyglot | 28% | — |
| SciCode | 27.4% | — |
| WeirdML | 30.7% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| LMArena Coding | 1286 | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Haiku: 28.0 (#95), Granite 4.0 Micro: —
| Benchmark | Claude 3.5 Haiku | Granite 4.0 Micro |
|---|---|---|
| BALROG | 19.3% | — |
Reasoning Granite 4.0 Micro leads
Claude 3.5 Haiku: 17.7 (#290), Granite 4.0 Micro: 19.2 (#265)
| Benchmark | Claude 3.5 Haiku | Granite 4.0 Micro |
|---|---|---|
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 28.1% | — |
| LMArena Hard Prompts | 1251 | — |
| DTBench | 56.7% | — |
| LiveBench Data Analysis | 48.5% | — |
| Epoch Capabilities Index | 127.15 | — |
| LiveBench | 43.5% | — |
Math Claude 3.5 Haiku leads
Claude 3.5 Haiku: 14.7 (#300), Granite 4.0 Micro: 12.0 (#307)
| Benchmark | Claude 3.5 Haiku | Granite 4.0 Micro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 2.8% |
| Omni-MATH | 22.4% | 20.9% |
| LiveBench Math | 35.5% | — |
| LMArena Math | 1244 | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Claude 3.5 Haiku leads
Claude 3.5 Haiku: 18.7 (#281), Granite 4.0 Micro: 9.9 (#304)
| Benchmark | Claude 3.5 Haiku | Granite 4.0 Micro |
|---|---|---|
| GPQA Diamond | 38.1% | 28.3% |
| MMLU-Pro | 60.5% | 39.5% |
| GPQA (HELM) | 36.3% | 30.7% |
| Confabulations | 36.7% | — |
| LMArena Expert | 1208 | — |
| MMLU | 74.3% | — |
Multimodal Not comparable
Claude 3.5 Haiku: 26.8 (#117), Granite 4.0 Micro: —
| Benchmark | Claude 3.5 Haiku | Granite 4.0 Micro |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
Multilingual Not comparable
Claude 3.5 Haiku: 40.0 (#218), Granite 4.0 Micro: —
| Benchmark | Claude 3.5 Haiku | Granite 4.0 Micro |
|---|---|---|
| LMArena Non-English | 1238 | — |
| LMArena Chinese | 1229 | — |
| LMArena French | 1264 | — |
| LMArena German | 1237 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1173 | — |
| LMArena Russian | 1253 | — |
| LMArena Spanish | 1261 | — |
Instruction Following Granite 4.0 Micro leads
Claude 3.5 Haiku: 62.9 (#234), Granite 4.0 Micro: 69.9 (#169)
| Benchmark | Claude 3.5 Haiku | Granite 4.0 Micro |
|---|---|---|
| IFEval | 79.2% | 84.9% |
| LiveBench Instruction Following | 61.9% | — |
| LMArena Instruction Following | 1241 | — |
Long Context Not comparable
Claude 3.5 Haiku: 38.3 (#200), Granite 4.0 Micro: —
| Benchmark | Claude 3.5 Haiku | Granite 4.0 Micro |
|---|---|---|
| LMArena Longer Query | 1261 | — |
Writing & Preference Granite 4.0 Micro leads
Claude 3.5 Haiku: 42.7 (#234), Granite 4.0 Micro: 46.7 (#216)
| Benchmark | Claude 3.5 Haiku | Granite 4.0 Micro |
|---|---|---|
| WildBench | 76% | 67% |
| LMArena Text | 1255 | — |
| LMArena Creative Writing | 1233 | — |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | 1146 | — |
| LMArena Multi-Turn | 1265 | — |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Granite 4.0 Micro?
Claude 3.5 Haiku and Granite 4.0 Micro score almost the same on the Noometry Index (29.2 vs 29.0), so choose on price, context window or the category you care about most.
How many benchmarks do Claude 3.5 Haiku and Granite 4.0 Micro share?
7 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Granite 4.0 Micro has 8.