Model comparison
Granite 4.1 8b vs Llama 3.1-70B
Granite 4.1 8b is the stronger model overall, scoring 37.4 to 29.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
MetaSummary
- They share 12 benchmarks with published results for both. Granite 4.1 8b scores higher in 7 categories and Llama 3.1-70B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Granite 4.1 8b leads 36.4 to 13.5.
Side by side
| Granite 4.1 8b | Llama 3.1-70B | |
|---|---|---|
| Provider | IBM | Meta |
| Noometry Index | 37.4 | 29.6 |
| Released | — | 2024-07-23 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 13 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Granite 4.1 8b: 30.1 (#297), Llama 3.1-70B: 30.3 (#296)
| Benchmark | Granite 4.1 8b | Llama 3.1-70B |
|---|---|---|
| LMArena Coding | 1312 | 1260 |
| LMArena WebDev | 1192 | — |
| WeirdML | — | 9% |
| BigCodeBench Instruct | — | 46.1% |
| BigCodeBench Complete | — | 54.8% |
Agentic & Tool Use Not comparable
Granite 4.1 8b: —, Llama 3.1-70B: 25.1 (#112)
| Benchmark | Granite 4.1 8b | Llama 3.1-70B |
|---|---|---|
| TheAgentCompany | — | 6.9% |
| BALROG | — | 27.9% |
Reasoning Granite 4.1 8b leads
Granite 4.1 8b: 25.7 (#143), Llama 3.1-70B: 21.6 (#220)
| Benchmark | Granite 4.1 8b | Llama 3.1-70B |
|---|---|---|
| LMArena Hard Prompts | 1293 | 1241 |
| DTBench | — | 60% |
| LMCA | — | 14.8% |
| Epoch Capabilities Index | — | 125.92 |
Math Granite 4.1 8b leads
Granite 4.1 8b: 36.4 (#166), Llama 3.1-70B: 13.5 (#304)
| Benchmark | Granite 4.1 8b | Llama 3.1-70B |
|---|---|---|
| LMArena Math | 1312 | 1252 |
| OTIS Mock AIME 2024-2025 | — | 3.6% |
| Omni-MATH | — | 21% |
| MATH Level 5 | — | 36.7% |
Knowledge Granite 4.1 8b leads
Granite 4.1 8b: 36.1 (#174), Llama 3.1-70B: 24.2 (#269)
| Benchmark | Granite 4.1 8b | Llama 3.1-70B |
|---|---|---|
| LMArena Expert | 1309 | 1209 |
| GPQA Diamond | — | 44.2% |
| MMLU-Pro | — | 65.3% |
| GPQA (HELM) | — | 42.6% |
| MMLU | — | 80.1% |
Multilingual Granite 4.1 8b leads
Granite 4.1 8b: 41.7 (#204), Llama 3.1-70B: 38.8 (#225)
| Benchmark | Granite 4.1 8b | Llama 3.1-70B |
|---|---|---|
| LMArena Non-English | 1261 | 1219 |
| LMArena Chinese | 1337 | 1215 |
| LMArena Russian | 1240 | 1234 |
| LMArena French | — | 1261 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1132 |
| LMArena Korean | — | 1140 |
| LMArena Spanish | — | 1253 |
Instruction Following Granite 4.1 8b leads
Granite 4.1 8b: 66.9 (#203), Llama 3.1-70B: 65.3 (#223)
| Benchmark | Granite 4.1 8b | Llama 3.1-70B |
|---|---|---|
| LMArena Instruction Following | 1269 | 1231 |
| IFEval | — | 82.1% |
Long Context Granite 4.1 8b leads
Granite 4.1 8b: 38.7 (#193), Llama 3.1-70B: 37.6 (#214)
| Benchmark | Granite 4.1 8b | Llama 3.1-70B |
|---|---|---|
| LMArena Longer Query | 1275 | 1241 |
Writing & Preference Granite 4.1 8b leads
Granite 4.1 8b: 48.1 (#204), Llama 3.1-70B: 35.4 (#267)
| Benchmark | Granite 4.1 8b | Llama 3.1-70B |
|---|---|---|
| LMArena Text | 1290 | 1261 |
| LMArena Creative Writing | 1251 | 1232 |
| LMArena Multi-Turn | 1268 | 1256 |
| EQ-Bench Creative Writing | — | 784 |
| WildBench | — | 75.8% |
Frequently asked questions
Is Granite 4.1 8b better than Llama 3.1-70B?
Granite 4.1 8b is the stronger model overall, scoring 37.4 to 29.6 on the Noometry Index.
Is Granite 4.1 8b or Llama 3.1-70B better for coding?
They score almost the same on coding (30.1 vs 30.3); test both on your own repository before choosing.
How many benchmarks do Granite 4.1 8b and Llama 3.1-70B share?
12 benchmarks have published results for both models. Granite 4.1 8b has 13 scored results on Noometry and Llama 3.1-70B has 35.