Model comparison
GLM-5.1 vs Qwen2.5 72B Instruct
GLM-5.1 is the stronger model overall, scoring 47.8 to 31.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. GLM-5.1 scores higher in 9 categories and Qwen2.5 72B Instruct in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.1 leads 49.7 to 19.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 8.1% for Qwen2.5 72B Instruct.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- GLM-5.1 accepts more context: 200K tokens versus 131K.
Side by side
| GLM-5.1 | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 47.8 | 31.9 |
| Released | 2026-04-07 | 2024-09 |
| Weights | Open | Open |
| Context window | 200K | 131K |
| Max output | 131K | 8K |
| Input $ / M tokens | $1.40 | $1.40 |
| Output $ / M tokens | $4.40 | $5.60 |
| Results tracked | 41 | 43 |
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), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | GLM-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | 57.1% | 16% |
| LMArena Coding | 1485 | 1292 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1508 | — |
| SciCode | 43.8% | — |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
| ALE-Bench | 887.1 | — |
Agentic & Tool Use GLM-5.1 leads
GLM-5.1: 24.9 (#113), Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | GLM-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| APEX-Agents | 40.9% | — |
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| METR Time Horizons | — | 35.8% |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | GLM-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1472 | 1271 |
| Epoch Capabilities Index | 149.84 | 129 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math GLM-5.1 leads
GLM-5.1: 49.7 (#60), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | GLM-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 8.1% |
| LMArena Math | 1473 | 1283 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | GLM-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 89.9% | 49.1% |
| LMArena Expert | 1476 | 1245 |
| SimpleQA Verified | 34% | — |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | GLM-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1447 | 1252 |
| LMArena Chinese | 1515 | 1272 |
| LMArena French | 1474 | 1280 |
| LMArena German | 1465 | 1234 |
| LMArena Japanese | 1434 | 1180 |
| LMArena Korean | 1418 | 1188 |
| LMArena Russian | 1454 | 1264 |
| LMArena Spanish | 1469 | 1256 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | GLM-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1451 | 1254 |
| IFEval | — | 80.6% |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#53), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | GLM-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1466 | 1282 |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | GLM-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1461 | 1269 |
| LMArena Creative Writing | 1453 | 1221 |
| LMArena Multi-Turn | 1472 | 1272 |
| EQ-Bench Creative Writing | 1592 | — |
| WildBench | — | 80.2% |
Frequently asked questions
Is GLM-5.1 better than Qwen2.5 72B Instruct?
GLM-5.1 is the stronger model overall, scoring 47.8 to 31.9 on the Noometry Index.
Which is cheaper, GLM-5.1 or Qwen2.5 72B Instruct?
GLM-5.1 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is GLM-5.1 or Qwen2.5 72B Instruct better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 33.2 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 Qwen2.5 72B Instruct share?
21 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Qwen2.5 72B Instruct has 43.