Model comparison
Granite 3.1 8b Instruct vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.7 to 32.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 3 categories and Qwen Max in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen Max leads 47.8 to 35.5.
- Granite 3.1 8b Instruct has downloadable open weights; the other is API-only.
Side by side
| Granite 3.1 8b Instruct | Qwen Max | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 32.4 | 34.7 |
| Released | — | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | — | 33K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.60 |
| Output $ / M tokens | — | $6.40 |
| Results tracked | 13 | 23 |
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), Qwen Max: 30.7 (#292)
| Benchmark | Granite 3.1 8b Instruct | Qwen Max |
|---|---|---|
| LMArena Coding | 1186 | 1288 |
| Aider Polyglot | — | 21.8% |
Agentic & Tool Use Not comparable
Granite 3.1 8b Instruct: 24.1 (#120), Qwen Max: —
| Benchmark | Granite 3.1 8b Instruct | Qwen Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Qwen Max leads
Granite 3.1 8b Instruct: 22.1 (#207), Qwen Max: 25.1 (#151)
| Benchmark | Granite 3.1 8b Instruct | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1145 | 1269 |
Math Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 33.0 (#209), Qwen Max: 22.3 (#276)
| Benchmark | Granite 3.1 8b Instruct | Qwen Max |
|---|---|---|
| LMArena Math | 1152 | 1275 |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Too close to call
Granite 3.1 8b Instruct: 31.1 (#220), Qwen Max: 30.3 (#228)
| Benchmark | Granite 3.1 8b Instruct | Qwen Max |
|---|---|---|
| LMArena Expert | 1142 | 1248 |
| GPQA Diamond | — | 56.1% |
Multilingual Qwen Max leads
Granite 3.1 8b Instruct: 30.9 (#260), Qwen Max: 41.8 (#202)
| Benchmark | Granite 3.1 8b Instruct | Qwen Max |
|---|---|---|
| LMArena Non-English | 1099 | 1263 |
| LMArena Chinese | 1145 | 1254 |
| LMArena Russian | 1092 | 1274 |
| LMArena French | — | 1330 |
| LMArena German | — | 1254 |
| LMArena Japanese | — | 1205 |
| LMArena Korean | — | 1142 |
| LMArena Spanish | — | 1290 |
Instruction Following Qwen Max leads
Granite 3.1 8b Instruct: 58.6 (#259), Qwen Max: 66.5 (#208)
| Benchmark | Granite 3.1 8b Instruct | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1131 | 1262 |
Long Context Qwen Max leads
Granite 3.1 8b Instruct: 35.2 (#241), Qwen Max: 39.4 (#180)
| Benchmark | Granite 3.1 8b Instruct | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1162 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Qwen Max leads
Granite 3.1 8b Instruct: 35.5 (#266), Qwen Max: 47.8 (#205)
| Benchmark | Granite 3.1 8b Instruct | Qwen Max |
|---|---|---|
| LMArena Text | 1150 | 1282 |
| LMArena Creative Writing | 1129 | 1248 |
| LMArena Multi-Turn | 1108 | 1277 |
Frequently asked questions
Is Granite 3.1 8b Instruct better than Qwen Max?
Qwen Max is the stronger model overall, scoring 34.7 to 32.4 on the Noometry Index.
Is Granite 3.1 8b Instruct or Qwen Max better for coding?
Granite 3.1 8b Instruct scores higher on coding benchmarks: 34.5 versus 30.7 in the Noometry coding category.
How many benchmarks do Granite 3.1 8b Instruct and Qwen Max share?
12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Qwen Max has 23.