Model comparison
Granite 4.2 30b vs Qwen3.5-Flash
Granite 4.2 30b and Qwen3.5-Flash score almost the same on the Noometry Index (41.4 vs 42.3), so choose on price, context window or the category you care about most.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Granite 4.2 30b scores higher in 1 category and Qwen3.5-Flash in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Granite 4.2 30b leads 40.4 to 33.9.
- Granite 4.2 30b has downloadable open weights; the other is API-only.
Side by side
| Granite 4.2 30b | Qwen3.5-Flash | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 41.4 | 42.3 |
| Released | — | 2026-02-23 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 11 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 30b leads
Granite 4.2 30b: 40.4 (#127), Qwen3.5-Flash: 33.9 (#234)
| Benchmark | Granite 4.2 30b | Qwen3.5-Flash |
|---|---|---|
| LMArena Coding | 1394 | 1412 |
| LMArena WebDev | — | 1243 |
| ALE-Bench | — | 221.8 |
Agentic & Tool Use Not comparable
Granite 4.2 30b: —, Qwen3.5-Flash: —
| Benchmark | Granite 4.2 30b | Qwen3.5-Flash |
|---|---|---|
| Vending-Bench 2 | — | 462.69 |
Reasoning Qwen3.5-Flash leads
Granite 4.2 30b: 26.7 (#114), Qwen3.5-Flash: 32.9 (#63)
| Benchmark | Granite 4.2 30b | Qwen3.5-Flash |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1404 |
| Chess Puzzles | — | 21% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 82.9% |
| LMCA | — | 29.1% |
| Epoch Capabilities Index | — | 143.98 |
Math Not comparable
Granite 4.2 30b: —, Qwen3.5-Flash: 36.3 (#117)
| Benchmark | Granite 4.2 30b | Qwen3.5-Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 18.2% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| LMArena Math | — | 1407 |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3.5-Flash leads
Granite 4.2 30b: 38.5 (#134), Qwen3.5-Flash: 43.2 (#84)
| Benchmark | Granite 4.2 30b | Qwen3.5-Flash |
|---|---|---|
| LMArena Expert | 1405 | 1408 |
| GPQA Diamond | — | 82.3% |
| SimpleQA Verified | — | 20.3% |
| Vectara Hallucination Rate | — | 10.5% |
Multilingual Qwen3.5-Flash leads
Granite 4.2 30b: 47.4 (#146), Qwen3.5-Flash: 50.7 (#116)
| Benchmark | Granite 4.2 30b | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1340 | 1385 |
| LMArena Chinese | 1415 | 1446 |
| LMArena Russian | 1342 | 1379 |
| LMArena French | — | 1412 |
| LMArena German | — | 1389 |
| LMArena Japanese | — | 1369 |
| LMArena Korean | — | 1344 |
| LMArena Spanish | — | 1399 |
Instruction Following Qwen3.5-Flash leads
Granite 4.2 30b: 71.3 (#150), Qwen3.5-Flash: 72.8 (#133)
| Benchmark | Granite 4.2 30b | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1346 | 1374 |
Long Context Qwen3.5-Flash leads
Granite 4.2 30b: 41.4 (#135), Qwen3.5-Flash: 42.4 (#119)
| Benchmark | Granite 4.2 30b | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1359 | 1392 |
Writing & Preference Qwen3.5-Flash leads
Granite 4.2 30b: 54.3 (#147), Qwen3.5-Flash: 58.2 (#117)
| Benchmark | Granite 4.2 30b | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1363 | 1397 |
| LMArena Creative Writing | 1294 | 1343 |
| LMArena Multi-Turn | 1340 | 1393 |
Frequently asked questions
Is Granite 4.2 30b better than Qwen3.5-Flash?
Granite 4.2 30b and Qwen3.5-Flash score almost the same on the Noometry Index (41.4 vs 42.3), so choose on price, context window or the category you care about most.
Is Granite 4.2 30b or Qwen3.5-Flash better for coding?
Granite 4.2 30b scores higher on coding benchmarks: 40.4 versus 33.9 in the Noometry coding category.
How many benchmarks do Granite 4.2 30b and Qwen3.5-Flash share?
11 benchmarks have published results for both models. Granite 4.2 30b has 11 scored results on Noometry and Qwen3.5-Flash has 32.