Model comparison
Granite 3.1 8b Instruct vs Llama 3.1-405B
Granite 3.1 8b Instruct is the stronger model overall, scoring 32.4 to 30.7 on the Noometry Index.
Last verified . 12 shared benchmarks.
MetaSummary
- They share 12 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 5 categories and Llama 3.1-405B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Granite 3.1 8b Instruct leads 33.0 to 18.4.
Side by side
| Granite 3.1 8b Instruct | Llama 3.1-405B | |
|---|---|---|
| Provider | IBM | Meta |
| Noometry Index | 32.4 | 30.7 |
| Released | — | 2024-07-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 34.5 (#233), Llama 3.1-405B: 33.1 (#262)
| Benchmark | Granite 3.1 8b Instruct | Llama 3.1-405B |
|---|---|---|
| LMArena Coding | 1186 | 1291 |
| WeirdML | — | 21.4% |
Agentic & Tool Use Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 24.1 (#120), Llama 3.1-405B: 21.0 (#140)
| Benchmark | Granite 3.1 8b Instruct | Llama 3.1-405B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
Reasoning Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 22.1 (#207), Llama 3.1-405B: 16.8 (#300)
| Benchmark | Granite 3.1 8b Instruct | Llama 3.1-405B |
|---|---|---|
| LMArena Hard Prompts | 1145 | 1269 |
| SimpleBench | — | 23% |
| Kagi LLM Benchmark | — | 45% |
| DTBench | — | 61.4% |
| BIG-Bench Hard | — | 82.9% |
| Epoch Capabilities Index | — | 128.75 |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 33.0 (#209), Llama 3.1-405B: 18.4 (#290)
| Benchmark | Granite 3.1 8b Instruct | Llama 3.1-405B |
|---|---|---|
| LMArena Math | 1152 | 1281 |
| OTIS Mock AIME 2024-2025 | — | 9.7% |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |
Knowledge Too close to call
Granite 3.1 8b Instruct: 31.1 (#220), Llama 3.1-405B: 30.4 (#227)
| Benchmark | Granite 3.1 8b Instruct | Llama 3.1-405B |
|---|---|---|
| LMArena Expert | 1142 | 1243 |
| GPQA Diamond | — | 50.9% |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |
Multilingual Llama 3.1-405B leads
Granite 3.1 8b Instruct: 30.9 (#260), Llama 3.1-405B: 40.7 (#214)
| Benchmark | Granite 3.1 8b Instruct | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1099 | 1248 |
| LMArena Chinese | 1145 | 1242 |
| LMArena Russian | 1092 | 1265 |
| LMArena French | — | 1279 |
| LMArena German | — | 1252 |
| LMArena Japanese | — | 1208 |
| LMArena Korean | — | 1184 |
| LMArena Spanish | — | 1260 |
Instruction Following Llama 3.1-405B leads
Granite 3.1 8b Instruct: 58.6 (#259), Llama 3.1-405B: 65.9 (#214)
| Benchmark | Granite 3.1 8b Instruct | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1131 | 1259 |
| IFEval | — | 81.1% |
Long Context Llama 3.1-405B leads
Granite 3.1 8b Instruct: 35.2 (#241), Llama 3.1-405B: 38.4 (#197)
| Benchmark | Granite 3.1 8b Instruct | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1162 | 1266 |
Writing & Preference Llama 3.1-405B leads
Granite 3.1 8b Instruct: 35.5 (#266), Llama 3.1-405B: 38.9 (#251)
| Benchmark | Granite 3.1 8b Instruct | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1150 | 1284 |
| LMArena Creative Writing | 1129 | 1262 |
| LMArena Multi-Turn | 1108 | 1297 |
| EQ-Bench Creative Writing | — | 870 |
| WildBench | — | 78.3% |
Frequently asked questions
Is Granite 3.1 8b Instruct better than Llama 3.1-405B?
Granite 3.1 8b Instruct is the stronger model overall, scoring 32.4 to 30.7 on the Noometry Index.
Is Granite 3.1 8b Instruct or Llama 3.1-405B better for coding?
Granite 3.1 8b Instruct scores higher on coding benchmarks: 34.5 versus 33.1 in the Noometry coding category.
How many benchmarks do Granite 3.1 8b Instruct and Llama 3.1-405B share?
12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Llama 3.1-405B has 42.