Model comparison
GLM-5.1 vs Mistral Large
GLM-5.1 is the stronger model overall, scoring 47.8 to 31.9 on the Noometry Index.
Last verified . 26 shared benchmarks.
Mistral AISummary
- They share 26 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Mistral Large in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.1 leads 49.7 to 18.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 8.5% for Mistral Large.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $2 / $6 for Mistral Large.
- GLM-5.1 accepts more context: 200K tokens versus 131K.
Side by side
| GLM-5.1 | Mistral Large | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 47.8 | 31.9 |
| Released | 2026-04-07 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 200K | 131K |
| Max output | 131K | 16K |
| Input $ / M tokens | $1.40 | $2 |
| Output $ / M tokens | $4.40 | $6 |
| Results tracked | 41 | 51 |
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), Mistral Large: 34.3 (#240)
| Benchmark | GLM-5.1 | Mistral Large |
|---|---|---|
| SciCode | 43.8% | 36.2% |
| LMArena Coding | 1485 | 1277 |
| ALE-Bench | 887.1 | 264.7 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1508 | — |
| WeirdML | 57.1% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Mistral Large leads
GLM-5.1: 24.9 (#113), Mistral Large: 28.6 (#89)
| Benchmark | GLM-5.1 | Mistral Large |
|---|---|---|
| APEX-Agents | 40.9% | — |
| Berkeley Function Calling Leaderboard | — | 38.4% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), Mistral Large: 15.8 (#310)
| Benchmark | GLM-5.1 | Mistral Large |
|---|---|---|
| SimpleBench | 55.1% | 22.5% |
| CritPt | 4.6% | 0% |
| LMArena Hard Prompts | 1472 | 1257 |
| Epoch Capabilities Index | 149.84 | 128.52 |
| NYT Connections (extended) | 77.7% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| LiveBench Reasoning | — | 43.5% |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math GLM-5.1 leads
GLM-5.1: 49.7 (#60), Mistral Large: 18.2 (#291)
| Benchmark | GLM-5.1 | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 8.5% |
| LMArena Math | 1473 | 1262 |
| FrontierMath (Feb 2025 set) | 33.4% | 0.3% |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), Mistral Large: 30.1 (#230)
| Benchmark | GLM-5.1 | Mistral Large |
|---|---|---|
| GPQA Diamond | 89.9% | 51.3% |
| LMArena Expert | 1476 | 1232 |
| SimpleQA Verified | 34% | — |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), Mistral Large: 40.0 (#219)
| Benchmark | GLM-5.1 | Mistral Large |
|---|---|---|
| LMArena Non-English | 1447 | 1237 |
| LMArena Chinese | 1515 | 1240 |
| LMArena French | 1474 | 1325 |
| LMArena German | 1465 | 1254 |
| LMArena Japanese | 1434 | 1188 |
| LMArena Korean | 1418 | 1202 |
| LMArena Russian | 1454 | 1257 |
| LMArena Spanish | 1469 | 1268 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), Mistral Large: 67.9 (#191)
| Benchmark | GLM-5.1 | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1451 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#53), Mistral Large: 38.3 (#199)
| Benchmark | GLM-5.1 | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1466 | 1261 |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), Mistral Large: 40.7 (#242)
| Benchmark | GLM-5.1 | Mistral Large |
|---|---|---|
| LMArena Text | 1461 | 1266 |
| LMArena Creative Writing | 1453 | 1243 |
| EQ-Bench Creative Writing | 1592 | 985 |
| LMArena Multi-Turn | 1472 | 1260 |
| Short-Story Creative Writing | — | 69% |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is GLM-5.1 better than Mistral Large?
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 Mistral Large?
GLM-5.1 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Mistral Large lists at $2 and $6.
Is GLM-5.1 or Mistral Large better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 34.3 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 Mistral Large share?
26 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Mistral Large has 51.