Model comparison
Claude 3 Haiku vs Granite 4.2 8B
Granite 4.2 8B is the stronger model overall, scoring 40.0 to 25.7 on the Noometry Index.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Granite 4.2 8B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.2 8B leads 37.7 to 17.3.
- Granite 4.2 8B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | Granite 4.2 8B | |
|---|---|---|
| Provider | Anthropic | IBM |
| Noometry Index | 25.7 | 40.0 |
| Released | 2024-03-07 | — |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 118K |
| Input $ / M tokens | — | $0.06 |
| Output $ / M tokens | — | $0.25 |
| Results tracked | 37 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 8B leads
Claude 3 Haiku: 26.1 (#320), Granite 4.2 8B: 39.9 (#138)
| Benchmark | Claude 3 Haiku | Granite 4.2 8B |
|---|---|---|
| LMArena Coding | 1199 | 1379 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Granite 4.2 8B leads
Claude 3 Haiku: 15.7 (#303), Granite 4.2 8B: 25.5 (#130)
| Benchmark | Claude 3 Haiku | Granite 4.2 8B |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1327 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.3 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Not comparable
Claude 3 Haiku: 9.2 (#313), Granite 4.2 8B: —
| Benchmark | Claude 3 Haiku | Granite 4.2 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| LMArena Math | 1188 | — |
| MATH Level 5 | 14.9% | — |
Knowledge Granite 4.2 8B leads
Claude 3 Haiku: 17.3 (#280), Granite 4.2 8B: 37.7 (#144)
| Benchmark | Claude 3 Haiku | Granite 4.2 8B |
|---|---|---|
| LMArena Expert | 1148 | 1380 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.1 (#123), Granite 4.2 8B: —
| Benchmark | Claude 3 Haiku | Granite 4.2 8B |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Granite 4.2 8B leads
Claude 3 Haiku: 36.1 (#238), Granite 4.2 8B: 44.5 (#173)
| Benchmark | Claude 3 Haiku | Granite 4.2 8B |
|---|---|---|
| LMArena Non-English | 1178 | 1299 |
| LMArena Chinese | 1155 | 1361 |
| LMArena Russian | 1204 | 1283 |
| LMArena French | 1194 | — |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1108 | — |
| LMArena Spanish | 1165 | — |
Instruction Following Granite 4.2 8B leads
Claude 3 Haiku: 61.5 (#242), Granite 4.2 8B: 68.7 (#183)
| Benchmark | Claude 3 Haiku | Granite 4.2 8B |
|---|---|---|
| LMArena Instruction Following | 1174 | 1298 |
Long Context Granite 4.2 8B leads
Claude 3 Haiku: 36.1 (#232), Granite 4.2 8B: 40.2 (#154)
| Benchmark | Claude 3 Haiku | Granite 4.2 8B |
|---|---|---|
| LMArena Longer Query | 1191 | 1323 |
Writing & Preference Granite 4.2 8B leads
Claude 3 Haiku: 29.8 (#286), Granite 4.2 8B: 49.8 (#183)
| Benchmark | Claude 3 Haiku | Granite 4.2 8B |
|---|---|---|
| LMArena Text | 1195 | 1319 |
| LMArena Creative Writing | 1157 | 1238 |
| LMArena Multi-Turn | 1190 | 1299 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Granite 4.2 8B?
Granite 4.2 8B is the stronger model overall, scoring 40.0 to 25.7 on the Noometry Index.
Is Claude 3 Haiku or Granite 4.2 8B better for coding?
Granite 4.2 8B scores higher on coding benchmarks: 39.9 versus 26.1 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Granite 4.2 8B share?
11 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Granite 4.2 8B has 11.