Model comparison
GLM-4.6 vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 41.4 on the Noometry Index.
Last verified . 25 shared benchmarks.
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. GLM-4.6 scores higher in 4 categories and Qwen3 235B-A22B in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 50.4 to 39.1.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 47.4% for GLM-4.6 and 69.4% for Qwen3 235B-A22B.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
- GLM-4.6 accepts more context: 205K tokens versus 131K.
Side by side
| GLM-4.6 | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 41.4 | 43.5 |
| Released | 2025-09-30 | 2025-04 |
| Weights | Open | Open |
| Context window | 205K | 131K |
| Max output | 131K | 16K |
| Input $ / M tokens | $0.60 | $0.70 |
| Output $ / M tokens | $2.20 | $2.80 |
| Results tracked | 29 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
GLM-4.6: 40.1 (#148), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | GLM-4.6 | Qwen3 235B-A22B |
|---|---|---|
| SciCode | 38.4% | 42.4% |
| LMArena Coding | 1449 | 1445 |
| SWE-bench Verified (bash only) | 55.4% | — |
| Aider Polyglot | — | 59.6% |
| LMArena WebDev | 1340 | — |
| WeirdML | — | 41% |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use Qwen3 235B-A22B leads
GLM-4.6: 32.3 (#66), Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | GLM-4.6 | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 72.4% | 52.1% |
| Terminal-Bench | 24.5% | — |
| Vending-Bench 2 | — | -11.34 |
Reasoning GLM-4.6 leads
GLM-4.6: 23.7 (#172), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | GLM-4.6 | Qwen3 235B-A22B |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 69.4% |
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1440 | 1433 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| ARC-AGI-1 | — | 11% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 29.3% |
| Epoch Capabilities Index | — | 143.85 |
| ForecastBench | — | 59.7 |
Math Qwen3 235B-A22B leads
GLM-4.6: 39.1 (#111), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | GLM-4.6 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Math | 1432 | 1432 |
| FrontierMath (Feb 2025 set) | 3.8% | 8.5% |
| FrontierMath Tier 4 (v1) | 2.1% | 0% |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| Omni-MATH | — | 71.8% |
| MATH Level 5 | — | 68.9% |
Knowledge Qwen3 235B-A22B leads
GLM-4.6: 40.2 (#124), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | GLM-4.6 | Qwen3 235B-A22B |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 9.3% |
| LMArena Expert | 1431 | 1463 |
| GPQA Diamond | — | 80.1% |
| SimpleQA Verified | — | 40.4% |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| GPQA (HELM) | — | 72.7% |
Multilingual GLM-4.6 leads
GLM-4.6: 53.5 (#66), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | GLM-4.6 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1426 | 1409 |
| LMArena Chinese | 1499 | 1481 |
| LMArena French | 1459 | 1445 |
| LMArena German | 1447 | 1433 |
| LMArena Japanese | 1393 | 1399 |
| LMArena Korean | 1400 | 1391 |
| LMArena Russian | 1419 | 1411 |
| LMArena Spanish | 1436 | 1430 |
Instruction Following GLM-4.6 leads
GLM-4.6: 74.3 (#98), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | GLM-4.6 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1410 | 1408 |
| IFEval | — | 83.5% |
Long Context Qwen3 235B-A22B leads
GLM-4.6: 43.4 (#94), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | GLM-4.6 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1422 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.1 (#90), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | GLM-4.6 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1440 | 1419 |
| LMArena Creative Writing | 1411 | 1384 |
| EQ-Bench Creative Writing | 1411 | 1366 |
| LMArena Multi-Turn | 1427 | 1432 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 86.6% |
Frequently asked questions
Is GLM-4.6 better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 41.4 on the Noometry Index.
Which is cheaper, GLM-4.6 or Qwen3 235B-A22B?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.
Is GLM-4.6 or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
GLM-4.6 does, with 205K tokens against 131K.
How many benchmarks do GLM-4.6 and Qwen3 235B-A22B share?
25 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Qwen3 235B-A22B has 49.