Model comparison
Granite 3.1 8b Instruct vs Qwen3.5 35B-A3B
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 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 1 category and Qwen3.5 35B-A3B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 35B-A3B leads 57.9 to 35.5.
Side by side
| Granite 3.1 8b Instruct | Qwen3.5 35B-A3B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 32.4 | 42.0 |
| Released | — | 2026-02-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $2 |
| Results tracked | 13 | 28 |
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), Qwen3.5 35B-A3B: 33.8 (#251)
| Benchmark | Granite 3.1 8b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Coding | 1186 | 1410 |
| LMArena WebDev | — | 1254 |
| SciCode | — | 29.3% |
Agentic & Tool Use Not comparable
Granite 3.1 8b Instruct: 24.1 (#120), Qwen3.5 35B-A3B: —
| Benchmark | Granite 3.1 8b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Qwen3.5 35B-A3B leads
Granite 3.1 8b Instruct: 22.1 (#207), Qwen3.5 35B-A3B: 24.6 (#161)
| Benchmark | Granite 3.1 8b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1145 | 1400 |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 10% |
| DTBench | — | 80% |
| LMCA | — | 29.5% |
| Epoch Capabilities Index | — | 142.52 |
Math Qwen3.5 35B-A3B leads
Granite 3.1 8b Instruct: 33.0 (#209), Qwen3.5 35B-A3B: 39.9 (#97)
| Benchmark | Granite 3.1 8b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Math | 1152 | 1404 |
| MathArena Final-Answer Competitions | — | 56% |
| OTIS Mock AIME 2024-2025 | — | 70% |
Knowledge Qwen3.5 35B-A3B leads
Granite 3.1 8b Instruct: 31.1 (#220), Qwen3.5 35B-A3B: 47.8 (#79)
| Benchmark | Granite 3.1 8b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Expert | 1142 | 1408 |
| GPQA Diamond | — | 83.5% |
| Vectara Hallucination Rate | — | 10.5% |
Multilingual Qwen3.5 35B-A3B leads
Granite 3.1 8b Instruct: 30.9 (#260), Qwen3.5 35B-A3B: 50.0 (#127)
| Benchmark | Granite 3.1 8b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1099 | 1378 |
| LMArena Chinese | 1145 | 1457 |
| LMArena Russian | 1092 | 1376 |
| LMArena French | — | 1412 |
| LMArena German | — | 1367 |
| LMArena Japanese | — | 1325 |
| LMArena Korean | — | 1356 |
| LMArena Spanish | — | 1392 |
Instruction Following Qwen3.5 35B-A3B leads
Granite 3.1 8b Instruct: 58.6 (#259), Qwen3.5 35B-A3B: 72.8 (#128)
| Benchmark | Granite 3.1 8b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1131 | 1379 |
Long Context Qwen3.5 35B-A3B leads
Granite 3.1 8b Instruct: 35.2 (#241), Qwen3.5 35B-A3B: 42.4 (#127)
| Benchmark | Granite 3.1 8b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1162 | 1389 |
Writing & Preference Qwen3.5 35B-A3B leads
Granite 3.1 8b Instruct: 35.5 (#266), Qwen3.5 35B-A3B: 57.9 (#124)
| Benchmark | Granite 3.1 8b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1150 | 1395 |
| LMArena Creative Writing | 1129 | 1346 |
| LMArena Multi-Turn | 1108 | 1390 |
Frequently asked questions
Is Granite 3.1 8b Instruct better than Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 32.4 on the Noometry Index.
Is Granite 3.1 8b Instruct or Qwen3.5 35B-A3B better for coding?
They score almost the same on coding (34.5 vs 33.8); test both on your own repository before choosing.
How many benchmarks do Granite 3.1 8b Instruct and Qwen3.5 35B-A3B share?
12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Qwen3.5 35B-A3B has 28.