Model comparison
GLM-4.7 vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 42.0 on the Noometry Index.
Last verified . 30 shared benchmarks.
Alibaba (Qwen)Summary
- They share 30 benchmarks with published results for both. GLM-4.7 scores higher in 4 categories and Qwen3 235B-A22B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 50.4 to 38.6.
- The biggest single-benchmark swing is SimpleBench: 47.7% for GLM-4.7 and 31% for Qwen3 235B-A22B.
- GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
- GLM-4.7 accepts more context: 205K tokens versus 131K.
Side by side
| GLM-4.7 | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 42.0 | 43.5 |
| Released | 2025-12-22 | 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 | 36 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.7: 44.0 (#79), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | GLM-4.7 | Qwen3 235B-A22B |
|---|---|---|
| SciCode | 45.1% | 42.4% |
| LMArena Coding | 1454 | 1445 |
| Aider Polyglot | — | 59.6% |
| LMArena WebDev | 1435 | — |
| WeirdML | — | 41% |
| ALE-Bench | 399.48 | — |
Agentic & Tool Use Qwen3 235B-A22B leads
GLM-4.7: 26.5 (#103), Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | GLM-4.7 | Qwen3 235B-A22B |
|---|---|---|
| Vending-Bench 2 | 2,377 | -11.34 |
| Terminal-Bench | 33.4% | — |
| Berkeley Function Calling Leaderboard | — | 52.1% |
Reasoning GLM-4.7 leads
GLM-4.7: 24.3 (#164), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | GLM-4.7 | Qwen3 235B-A22B |
|---|---|---|
| SimpleBench | 47.7% | 31% |
| CritPt | 1.7% | 0% |
| Chess Puzzles | 6% | 12% |
| LMArena Hard Prompts | 1443 | 1433 |
| Epoch Capabilities Index | 143.51 | 143.85 |
| ARC-AGI-2 | — | 1.3% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 11% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 29.3% |
| ForecastBench | — | 59.7 |
Math Qwen3 235B-A22B leads
GLM-4.7: 38.6 (#135), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | GLM-4.7 | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 86.7% |
| LMArena Math | 1423 | 1432 |
| FrontierMath (Feb 2025 set) | 2.4% | 8.5% |
| FrontierMath Tier 4 (v1) | 0% | 0% |
| ProofBench | 6% | — |
| Omni-MATH | — | 71.8% |
| MATH Level 5 | — | 68.9% |
Knowledge Qwen3 235B-A22B leads
GLM-4.7: 47.0 (#80), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | GLM-4.7 | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 83.3% | 80.1% |
| SimpleQA Verified | 32.2% | 40.4% |
| Vectara Hallucination Rate | 11.7% | 9.3% |
| LMArena Expert | 1424 | 1463 |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| GPQA (HELM) | — | 72.7% |
Multilingual Too close to call
GLM-4.7: 52.8 (#79), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | GLM-4.7 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1417 | 1409 |
| LMArena Chinese | 1495 | 1481 |
| LMArena French | 1432 | 1445 |
| LMArena German | 1424 | 1433 |
| LMArena Japanese | 1439 | 1399 |
| LMArena Korean | 1399 | 1391 |
| LMArena Russian | 1423 | 1411 |
| LMArena Spanish | 1434 | 1430 |
Instruction Following GLM-4.7 leads
GLM-4.7: 74.4 (#95), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | GLM-4.7 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1411 | 1408 |
| IFEval | — | 83.5% |
Long Context Qwen3 235B-A22B leads
GLM-4.7: 42.8 (#116), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | GLM-4.7 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1432 | 1426 |
| Fiction.LiveBench | — | 75% |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference GLM-4.7 leads
GLM-4.7: 60.9 (#93), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | GLM-4.7 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1435 | 1419 |
| LMArena Creative Writing | 1401 | 1384 |
| EQ-Bench Creative Writing | 1413 | 1366 |
| LMArena Multi-Turn | 1446 | 1432 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 86.6% |
Frequently asked questions
Is GLM-4.7 better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 42.0 on the Noometry Index.
Which is cheaper, GLM-4.7 or Qwen3 235B-A22B?
GLM-4.7 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-4.7 or Qwen3 235B-A22B better for coding?
They score almost the same on coding (44.0 vs 44.3); test both on your own repository before choosing.
Which has the bigger context window?
GLM-4.7 does, with 205K tokens against 131K.
How many benchmarks do GLM-4.7 and Qwen3 235B-A22B share?
30 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Qwen3 235B-A22B has 49.