Model comparison
Granite 3.1 2b Instruct vs Llama 4 Maverick
Granite 3.1 2b Instruct is the stronger model overall, scoring 32.6 to 30.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
MetaSummary
- They share 12 benchmarks with published results for both. Granite 3.1 2b Instruct scores higher in 4 categories and Llama 4 Maverick in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 4 Maverick leads 71.9 to 58.0.
Side by side
| Granite 3.1 2b Instruct | Llama 4 Maverick | |
|---|---|---|
| Provider | IBM | Meta |
| Noometry Index | 32.6 | 30.6 |
| Released | — | 2025-04-05 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.19 |
| Output $ / M tokens | — | $0.65 |
| Results tracked | 12 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 32.9 (#255), Llama 4 Maverick: 26.3 (#318)
| Benchmark | Granite 3.1 2b Instruct | Llama 4 Maverick |
|---|---|---|
| LMArena Coding | 1149 | 1302 |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| SciCode | — | 33.1% |
| WeirdML | — | 24.5% |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |
| ALE-Bench | — | 172.97 |
Agentic & Tool Use Not comparable
Granite 3.1 2b Instruct: —, Llama 4 Maverick: 27.9 (#86)
| Benchmark | Granite 3.1 2b Instruct | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |
Reasoning Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 21.0 (#206), Llama 4 Maverick: 10.1 (#337)
| Benchmark | Granite 3.1 2b Instruct | Llama 4 Maverick |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1281 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 27.7% |
| Kagi LLM Benchmark | — | 55.9% |
| NYT Connections (extended) | — | 8% |
| ARC-AGI-1 | — | 4.4% |
| CritPt | — | 0% |
| EnigmaEval | — | 0.6% |
| DTBench | — | 61.9% |
| LMCA | — | 15.9% |
| Epoch Capabilities Index | — | 132.2 |
| ForecastBench | — | 57.5 |
Math Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 30.6 (#206), Llama 4 Maverick: 24.6 (#256)
| Benchmark | Granite 3.1 2b Instruct | Llama 4 Maverick |
|---|---|---|
| LMArena Math | 1159 | 1299 |
| OTIS Mock AIME 2024-2025 | — | 20.6% |
| Omni-MATH | — | 42.2% |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge Llama 4 Maverick leads
Granite 3.1 2b Instruct: 30.3 (#223), Llama 4 Maverick: 33.3 (#196)
| Benchmark | Granite 3.1 2b Instruct | Llama 4 Maverick |
|---|---|---|
| LMArena Expert | 1131 | 1259 |
| GPQA Diamond | — | 67% |
| Humanity's Last Exam | — | 5.7% |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| Vectara Hallucination Rate | — | 8.2% |
| GPQA (HELM) | — | 65% |
Multimodal Not comparable
Granite 3.1 2b Instruct: —, Llama 4 Maverick: 30.9 (#100)
| Benchmark | Granite 3.1 2b Instruct | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | — | 1141 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual Llama 4 Maverick leads
Granite 3.1 2b Instruct: 29.2 (#264), Llama 4 Maverick: 42.4 (#190)
| Benchmark | Granite 3.1 2b Instruct | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1068 | 1269 |
| LMArena Chinese | 1138 | 1277 |
| LMArena Russian | 1063 | 1286 |
| LMArena French | — | 1258 |
| LMArena German | — | 1291 |
| LMArena Japanese | — | 1207 |
| LMArena Korean | — | 1203 |
| LMArena Spanish | — | 1293 |
Instruction Following Llama 4 Maverick leads
Granite 3.1 2b Instruct: 58.0 (#259), Llama 4 Maverick: 71.9 (#140)
| Benchmark | Granite 3.1 2b Instruct | Llama 4 Maverick |
|---|---|---|
| LMArena Instruction Following | 1116 | 1267 |
| IFEval | — | 90.8% |
Long Context Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 35.0 (#239), Llama 4 Maverick: 31.4 (#274)
| Benchmark | Granite 3.1 2b Instruct | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1155 | 1280 |
| Fiction.LiveBench | — | 46.2% |
Writing & Preference Llama 4 Maverick leads
Granite 3.1 2b Instruct: 34.3 (#269), Llama 4 Maverick: 39.0 (#247)
| Benchmark | Granite 3.1 2b Instruct | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1127 | 1287 |
| LMArena Creative Writing | 1116 | 1266 |
| LMArena Multi-Turn | 1099 | 1289 |
| Short-Story Creative Writing | — | 62% |
| EQ-Bench Creative Writing | — | 860 |
| WildBench | — | 80% |
Frequently asked questions
Is Granite 3.1 2b Instruct better than Llama 4 Maverick?
Granite 3.1 2b Instruct is the stronger model overall, scoring 32.6 to 30.6 on the Noometry Index.
Is Granite 3.1 2b Instruct or Llama 4 Maverick better for coding?
Granite 3.1 2b Instruct scores higher on coding benchmarks: 32.9 versus 26.3 in the Noometry coding category.
How many benchmarks do Granite 3.1 2b Instruct and Llama 4 Maverick share?
12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Llama 4 Maverick has 54.