Model comparison
Granite 3.1 8b Instruct vs Qwen Plus
Qwen Plus is the stronger model overall, scoring 37.1 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 2 categories and Qwen Plus in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen Plus leads 52.2 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 Plus | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 32.4 | 37.1 |
| Released | — | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 13 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
Granite 3.1 8b Instruct: 34.5 (#233), Qwen Plus: 38.9 (#167)
| Benchmark | Granite 3.1 8b Instruct | Qwen Plus |
|---|---|---|
| LMArena Coding | 1186 | 1328 |
Agentic & Tool Use Not comparable
Granite 3.1 8b Instruct: 24.1 (#120), Qwen Plus: —
| Benchmark | Granite 3.1 8b Instruct | Qwen Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Qwen Plus leads
Granite 3.1 8b Instruct: 22.1 (#207), Qwen Plus: 28.4 (#107)
| Benchmark | Granite 3.1 8b Instruct | Qwen Plus |
|---|---|---|
| LMArena Hard Prompts | 1145 | 1317 |
| Kagi LLM Benchmark | — | 63.3% |
| DTBench | — | 81.1% |
| LMCA | — | 24% |
Math Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 33.0 (#209), Qwen Plus: 23.3 (#271)
| Benchmark | Granite 3.1 8b Instruct | Qwen Plus |
|---|---|---|
| LMArena Math | 1152 | 1326 |
| OTIS Mock AIME 2024-2025 | — | 17.8% |
| MATH Level 5 | — | 65.3% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 31.1 (#220), Qwen Plus: 27.4 (#251)
| Benchmark | Granite 3.1 8b Instruct | Qwen Plus |
|---|---|---|
| LMArena Expert | 1142 | 1328 |
| GPQA Diamond | — | 48.1% |
Multilingual Qwen Plus leads
Granite 3.1 8b Instruct: 30.9 (#260), Qwen Plus: 45.1 (#175)
| Benchmark | Granite 3.1 8b Instruct | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1099 | 1310 |
| LMArena Chinese | 1145 | 1347 |
| LMArena Russian | 1092 | 1323 |
| LMArena Japanese | — | 1251 |
Instruction Following Qwen Plus leads
Granite 3.1 8b Instruct: 58.6 (#259), Qwen Plus: 68.8 (#181)
| Benchmark | Granite 3.1 8b Instruct | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1131 | 1303 |
Long Context Qwen Plus leads
Granite 3.1 8b Instruct: 35.2 (#241), Qwen Plus: 40.3 (#158)
| Benchmark | Granite 3.1 8b Instruct | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1162 | 1324 |
Writing & Preference Qwen Plus leads
Granite 3.1 8b Instruct: 35.5 (#266), Qwen Plus: 52.2 (#176)
| Benchmark | Granite 3.1 8b Instruct | Qwen Plus |
|---|---|---|
| LMArena Text | 1150 | 1326 |
| LMArena Creative Writing | 1129 | 1293 |
| LMArena Multi-Turn | 1108 | 1336 |
Frequently asked questions
Is Granite 3.1 8b Instruct better than Qwen Plus?
Qwen Plus is the stronger model overall, scoring 37.1 to 32.4 on the Noometry Index.
Is Granite 3.1 8b Instruct or Qwen Plus better for coding?
Qwen Plus scores higher on coding benchmarks: 38.9 versus 34.5 in the Noometry coding category.
How many benchmarks do Granite 3.1 8b Instruct and Qwen Plus share?
12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Qwen Plus has 20.