Model comparison
Granite 3.1 8b Instruct vs Mistral Medium
Mistral Medium is the stronger model overall, scoring 36.3 to 32.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
Mistral AISummary
- They share 13 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 3 categories and Mistral Medium in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 35.5.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 27.1% for Granite 3.1 8b Instruct and 37.7% for Mistral Medium.
Side by side
| Granite 3.1 8b Instruct | Mistral Medium | |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 32.4 | 36.3 |
| Released | — | 2023-12-11 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 13 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Granite 3.1 8b Instruct: 34.5 (#233), Mistral Medium: 34.2 (#243)
| Benchmark | Granite 3.1 8b Instruct | Mistral Medium |
|---|---|---|
| LMArena Coding | 1186 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Mistral Medium leads
Granite 3.1 8b Instruct: 24.1 (#120), Mistral Medium: 28.3 (#90)
| Benchmark | Granite 3.1 8b Instruct | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | 37.7% |
Reasoning Mistral Medium leads
Granite 3.1 8b Instruct: 22.1 (#207), Mistral Medium: 24.0 (#167)
| Benchmark | Granite 3.1 8b Instruct | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1145 | 1426 |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
Math Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 33.0 (#209), Mistral Medium: 28.1 (#245)
| Benchmark | Granite 3.1 8b Instruct | Mistral Medium |
|---|---|---|
| LMArena Math | 1152 | 1408 |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 31.1 (#220), Mistral Medium: 25.0 (#265)
| Benchmark | Granite 3.1 8b Instruct | Mistral Medium |
|---|---|---|
| LMArena Expert | 1142 | 1408 |
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
Multimodal Not comparable
Granite 3.1 8b Instruct: —, Mistral Medium: 35.3 (#88)
| Benchmark | Granite 3.1 8b Instruct | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Mistral Medium leads
Granite 3.1 8b Instruct: 30.9 (#260), Mistral Medium: 52.1 (#91)
| Benchmark | Granite 3.1 8b Instruct | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1099 | 1408 |
| LMArena Chinese | 1145 | 1447 |
| LMArena Russian | 1092 | 1411 |
| LMArena French | — | 1459 |
| LMArena German | — | 1432 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1380 |
| LMArena Spanish | — | 1433 |
Instruction Following Mistral Medium leads
Granite 3.1 8b Instruct: 58.6 (#259), Mistral Medium: 73.7 (#116)
| Benchmark | Granite 3.1 8b Instruct | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1131 | 1398 |
Long Context Mistral Medium leads
Granite 3.1 8b Instruct: 35.2 (#241), Mistral Medium: 42.9 (#114)
| Benchmark | Granite 3.1 8b Instruct | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1162 | 1406 |
Writing & Preference Mistral Medium leads
Granite 3.1 8b Instruct: 35.5 (#266), Mistral Medium: 60.0 (#103)
| Benchmark | Granite 3.1 8b Instruct | Mistral Medium |
|---|---|---|
| LMArena Text | 1150 | 1424 |
| LMArena Creative Writing | 1129 | 1391 |
| LMArena Multi-Turn | 1108 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
Frequently asked questions
Is Granite 3.1 8b Instruct better than Mistral Medium?
Mistral Medium is the stronger model overall, scoring 36.3 to 32.4 on the Noometry Index.
Is Granite 3.1 8b Instruct or Mistral Medium better for coding?
They score almost the same on coding (34.5 vs 34.2); test both on your own repository before choosing.
How many benchmarks do Granite 3.1 8b Instruct and Mistral Medium share?
13 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Mistral Medium has 36.