Model comparison
GLM-5 vs Mistral Large
GLM-5 is the stronger model overall, scoring 46.1 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 scores higher in 9 categories and Mistral Large in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5 leads 46.4 to 18.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for GLM-5 and 8.5% for Mistral Large.
- GLM-5 is cheaper at $1 / $3.20 per million input/output tokens, against $2 / $6 for Mistral Large.
- GLM-5 accepts more context: 205K tokens versus 131K.
Side by side
| GLM-5 | Mistral Large | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 46.1 | 31.9 |
| Released | 2026-02-11 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 205K | 131K |
| Max output | 131K | 16K |
| Input $ / M tokens | $1 | $2 |
| Output $ / M tokens | $3.20 | $6 |
| Results tracked | 45 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), Mistral Large: 34.3 (#240)
| Benchmark | GLM-5 | Mistral Large |
|---|---|---|
| LMArena Coding | 1461 | 1277 |
| ALE-Bench | 765.62 | 264.7 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| SciCode | — | 36.2% |
| WeirdML | 48.2% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use GLM-5 leads
GLM-5: 31.1 (#71), Mistral Large: 28.6 (#89)
| Benchmark | GLM-5 | Mistral Large |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| Berkeley Function Calling Leaderboard | — | 38.4% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Vending-Bench 2 | 4,432 | — |
Reasoning GLM-5 leads
GLM-5: 27.6 (#116), Mistral Large: 15.8 (#310)
| Benchmark | GLM-5 | Mistral Large |
|---|---|---|
| SimpleBench | 53.2% | 22.5% |
| LMArena Hard Prompts | 1452 | 1257 |
| Epoch Capabilities Index | 145.83 | 128.52 |
| ForecastBench | 61 | 57.1 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 74.8% | — |
| ARC-AGI-1 | 44.7% | — |
| CritPt | — | 0% |
| Chess Puzzles | 10% | — |
| LiveBench Reasoning | — | 43.5% |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| LiveBench | — | 48.4% |
Math GLM-5 leads
GLM-5: 46.4 (#71), Mistral Large: 18.2 (#291)
| Benchmark | GLM-5 | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 8.5% |
| LMArena Math | 1440 | 1262 |
| FrontierMath (Feb 2025 set) | 16.4% | 0.3% |
| MathArena Final-Answer Competitions | 65.7% | — |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), Mistral Large: 30.1 (#230)
| Benchmark | GLM-5 | Mistral Large |
|---|---|---|
| GPQA Diamond | 87.8% | 51.3% |
| Vectara Hallucination Rate | 10.1% | 4.5% |
| LMArena Expert | 1454 | 1232 |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), Mistral Large: 40.0 (#219)
| Benchmark | GLM-5 | Mistral Large |
|---|---|---|
| LMArena Non-English | 1430 | 1237 |
| LMArena Chinese | 1511 | 1240 |
| LMArena French | 1455 | 1325 |
| LMArena German | 1445 | 1254 |
| LMArena Japanese | 1416 | 1188 |
| LMArena Korean | 1423 | 1202 |
| LMArena Russian | 1436 | 1257 |
| LMArena Spanish | 1454 | 1268 |
Instruction Following GLM-5 leads
GLM-5: 75.2 (#67), Mistral Large: 67.9 (#191)
| Benchmark | GLM-5 | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1428 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context GLM-5 leads
GLM-5: 44.7 (#60), Mistral Large: 38.3 (#199)
| Benchmark | GLM-5 | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1446 | 1261 |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), Mistral Large: 40.7 (#242)
| Benchmark | GLM-5 | Mistral Large |
|---|---|---|
| LMArena Text | 1446 | 1266 |
| LMArena Creative Writing | 1439 | 1243 |
| EQ-Bench Creative Writing | 1601 | 985 |
| LMArena Multi-Turn | 1456 | 1260 |
| Short-Story Creative Writing | — | 69% |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is GLM-5 better than Mistral Large?
GLM-5 is the stronger model overall, scoring 46.1 to 31.9 on the Noometry Index.
Which is cheaper, GLM-5 or Mistral Large?
GLM-5 is cheaper. It lists at $1 per million input tokens and $3.20 per million output tokens; Mistral Large lists at $2 and $6.
Is GLM-5 or Mistral Large better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
GLM-5 does, with 205K tokens against 131K.
How many benchmarks do GLM-5 and Mistral Large share?
26 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Mistral Large has 51.