Model comparison
GLM-5.1 vs Qwen3 235B-A22B
GLM-5.1 is the stronger model overall, scoring 47.8 to 43.5 on the Noometry Index. Qwen3 235B-A22B costs 1.8× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Last verified . 30 shared benchmarks.
Alibaba (Qwen)Summary
- They share 30 benchmarks with published results for both. GLM-5.1 scores higher in 6 categories and Qwen3 235B-A22B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 39.1 to 15.7.
- The biggest single-benchmark swing is SimpleBench: 55.1% for GLM-5.1 and 31% for Qwen3 235B-A22B.
- Qwen3 235B-A22B is cheaper at $0.70 / $2.80 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5.1 accepts more context: 200K tokens versus 131K.
Side by side
| GLM-5.1 | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 47.8 | 43.5 |
| Released | 2026-04-07 | 2025-04 |
| Weights | Open | Open |
| Context window | 200K | 131K |
| Max output | 131K | 16K |
| Input $ / M tokens | $1.40 | $0.70 |
| Output $ / M tokens | $4.40 | $2.80 |
| Results tracked | 41 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-5.1: 48.7 (#55), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | GLM-5.1 | Qwen3 235B-A22B |
|---|---|---|
| SciCode | 43.8% | 42.4% |
| WeirdML | 57.1% | 41% |
| LMArena Coding | 1485 | 1445 |
| SWE-bench Verified | 74.2% | — |
| Aider Polyglot | — | 59.6% |
| LMArena WebDev | 1508 | — |
| ALE-Bench | 887.1 | — |
Agentic & Tool Use Qwen3 235B-A22B leads
GLM-5.1: 24.9 (#113), Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | GLM-5.1 | Qwen3 235B-A22B |
|---|---|---|
| Vending-Bench 2 | 5,634 | -11.34 |
| APEX-Agents | 40.9% | — |
| Berkeley Function Calling Leaderboard | — | 52.1% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | GLM-5.1 | Qwen3 235B-A22B |
|---|---|---|
| SimpleBench | 55.1% | 31% |
| CritPt | 4.6% | 0% |
| Chess Puzzles | 19% | 12% |
| LMArena Hard Prompts | 1472 | 1433 |
| Epoch Capabilities Index | 149.84 | 143.85 |
| ARC-AGI-2 | — | 1.3% |
| Kagi LLM Benchmark | — | 69.4% |
| NYT Connections (extended) | 77.7% | — |
| ARC-AGI-1 | — | 11% |
| Thematic Generalization | 69.8% | — |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 29.3% |
| ForecastBench | — | 59.7 |
Math Too close to call
GLM-5.1: 49.7 (#60), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | GLM-5.1 | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 86.7% |
| LMArena Math | 1473 | 1432 |
| FrontierMath (Feb 2025 set) | 33.4% | 8.5% |
| FrontierMath Tier 4 (v1) | 12.5% | 0% |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| Omni-MATH | — | 71.8% |
| MATH Level 5 | — | 68.9% |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | GLM-5.1 | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 89.9% | 80.1% |
| SimpleQA Verified | 34% | 40.4% |
| LMArena Expert | 1476 | 1463 |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 72.7% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | GLM-5.1 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1447 | 1409 |
| LMArena Chinese | 1515 | 1481 |
| LMArena French | 1474 | 1445 |
| LMArena German | 1465 | 1433 |
| LMArena Japanese | 1434 | 1399 |
| LMArena Korean | 1418 | 1391 |
| LMArena Russian | 1454 | 1411 |
| LMArena Spanish | 1469 | 1430 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | GLM-5.1 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1451 | 1408 |
| IFEval | — | 83.5% |
Long Context Qwen3 235B-A22B leads
GLM-5.1: 44.9 (#53), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | GLM-5.1 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1466 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | GLM-5.1 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1461 | 1419 |
| LMArena Creative Writing | 1453 | 1384 |
| EQ-Bench Creative Writing | 1592 | 1366 |
| LMArena Multi-Turn | 1472 | 1432 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 86.6% |
Frequently asked questions
Is GLM-5.1 better than Qwen3 235B-A22B?
GLM-5.1 is the stronger model overall, scoring 47.8 to 43.5 on the Noometry Index. Qwen3 235B-A22B costs 1.8× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Which is cheaper, GLM-5.1 or Qwen3 235B-A22B?
Qwen3 235B-A22B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or Qwen3 235B-A22B better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 44.3 in the Noometry coding category.
Which has the bigger context window?
GLM-5.1 does, with 200K tokens against 131K.
How many benchmarks do GLM-5.1 and Qwen3 235B-A22B share?
30 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Qwen3 235B-A22B has 49.