Model comparison
Claude Sonnet 4 vs Granite 4.2 8B
Claude Sonnet 4 and Granite 4.2 8B score almost the same on the Noometry Index (40.8 vs 40.5), so choose on price, context window or the category you care about most.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. Claude Sonnet 4 scores higher in 5 categories and Granite 4.2 8B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Sonnet 4 leads 57.1 to 49.6.
- Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Claude Sonnet 4 accepts more context: 200K tokens versus 131K.
- Granite 4.2 8B has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | Granite 4.2 8B | |
|---|---|---|
| Provider | Anthropic | IBM |
| Noometry Index | 40.8 | 40.5 |
| Released | 2025-05-22 | — |
| Weights | Proprietary | Open |
| Context window | 200K | 131K |
| Max output | 64K | 118K |
| Input $ / M tokens | $3 | $0.06 |
| Output $ / M tokens | $15 | $0.25 |
| Results tracked | 58 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), Granite 4.2 8B: 40.5 (#137)
| Benchmark | Claude Sonnet 4 | Granite 4.2 8B |
|---|---|---|
| LMArena Coding | 1414 | 1380 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4: 38.5 (#31), Granite 4.2 8B: —
| Benchmark | Claude Sonnet 4 | Granite 4.2 8B |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Granite 4.2 8B leads
Claude Sonnet 4: 22.9 (#187), Granite 4.2 8B: 26.6 (#131)
| Benchmark | Claude Sonnet 4 | Granite 4.2 8B |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1329 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 3.1% | — |
| DTBench | 77.1% | — |
| LMCA | 29% | — |
| Epoch Capabilities Index | 141.69 | — |
| ForecastBench | 60.2 | — |
Math Not comparable
Claude Sonnet 4: 43.3 (#80), Granite 4.2 8B: —
| Benchmark | Claude Sonnet 4 | Granite 4.2 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| Omni-MATH | 60.2% | — |
| LMArena Math | 1375 | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), Granite 4.2 8B: 38.4 (#145)
| Benchmark | Claude Sonnet 4 | Granite 4.2 8B |
|---|---|---|
| LMArena Expert | 1372 | 1384 |
| GPQA Diamond | 79.2% | — |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Not comparable
Claude Sonnet 4: 26.2 (#121), Granite 4.2 8B: —
| Benchmark | Claude Sonnet 4 | Granite 4.2 8B |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Claude Sonnet 4 leads
Claude Sonnet 4: 46.7 (#156), Granite 4.2 8B: 44.5 (#178)
| Benchmark | Claude Sonnet 4 | Granite 4.2 8B |
|---|---|---|
| LMArena Non-English | 1333 | 1302 |
| LMArena Chinese | 1350 | 1366 |
| LMArena Russian | 1355 | 1285 |
| LMArena French | 1363 | — |
| LMArena German | 1331 | — |
| LMArena Japanese | 1302 | — |
| LMArena Korean | 1291 | — |
| LMArena Spanish | 1357 | — |
Instruction Following Claude Sonnet 4 leads
Claude Sonnet 4: 71.7 (#145), Granite 4.2 8B: 68.7 (#184)
| Benchmark | Claude Sonnet 4 | Granite 4.2 8B |
|---|---|---|
| LMArena Instruction Following | 1376 | 1301 |
| IFEval | 84% | — |
Long Context Granite 4.2 8B leads
Claude Sonnet 4: 33.7 (#259), Granite 4.2 8B: 40.3 (#159)
| Benchmark | Claude Sonnet 4 | Granite 4.2 8B |
|---|---|---|
| LMArena Longer Query | 1398 | 1324 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), Granite 4.2 8B: 49.6 (#189)
| Benchmark | Claude Sonnet 4 | Granite 4.2 8B |
|---|---|---|
| LMArena Text | 1351 | 1320 |
| LMArena Creative Writing | 1345 | 1236 |
| LMArena Multi-Turn | 1376 | 1301 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than Granite 4.2 8B?
Claude Sonnet 4 and Granite 4.2 8B score almost the same on the Noometry Index (40.8 vs 40.5), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Sonnet 4 or Granite 4.2 8B?
Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or Granite 4.2 8B better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 40.5 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 4 does, with 200K tokens against 131K.
How many benchmarks do Claude Sonnet 4 and Granite 4.2 8B share?
11 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Granite 4.2 8B has 11.