Model comparison
GLM-5.3-Flash vs Mistral Large
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 31.6 on the Noometry Index.
Last verified . 23 shared benchmarks.
Mistral AISummary
- They share 23 benchmarks with published results for both. GLM-5.3-Flash 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-5.3-Flash leads 53.1 to 17.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.9% for GLM-5.3-Flash and 8.5% for Mistral Large.
- GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $2 / $6 for Mistral Large.
- GLM-5.3-Flash accepts more context: 1M tokens versus 131K.
Side by side
| GLM-5.3-Flash | Mistral Large | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 49.6 | 31.6 |
| Released | 2026-08-20 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 1M | 131K |
| Max output | 131K | 16K |
| Input $ / M tokens | $0.15 | $2 |
| Output $ / M tokens | $0.50 | $6 |
| Results tracked | 36 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
GLM-5.3-Flash: 53.7 (#26), Mistral Large: 33.8 (#240)
| Benchmark | GLM-5.3-Flash | Mistral Large |
|---|---|---|
| SciCode | 51.6% | 36.2% |
| LMArena Coding | 1506 | 1277 |
| ALE-Bench | 303.55 | 264.7 |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| LMArena WebDev | 1614 | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use GLM-5.3-Flash leads
GLM-5.3-Flash: 34.3 (#41), Mistral Large: 28.4 (#83)
| Benchmark | GLM-5.3-Flash | Mistral Large |
|---|---|---|
| APEX-Agents | 52.8% | — |
| Berkeley Function Calling Leaderboard | — | 38.4% |
| GDP.pdf | 14% | — |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 31.7 (#69), Mistral Large: 15.4 (#305)
| Benchmark | GLM-5.3-Flash | Mistral Large |
|---|---|---|
| CritPt | 15.4% | 0% |
| LMArena Hard Prompts | 1490 | 1257 |
| Epoch Capabilities Index | 151.9 | 128.52 |
| SimpleBench | — | 22.5% |
| Chess Puzzles | 14% | — |
| LiveBench Reasoning | — | 43.5% |
| Mystery Game Puzzles | 8% | — |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| Surface Evolver Bench | 52.5% | — |
| Bench to the Future 3 | 0.15 | — |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math GLM-5.3-Flash leads
GLM-5.3-Flash: 53.1 (#38), Mistral Large: 17.1 (#285)
| Benchmark | GLM-5.3-Flash | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.9% | 8.5% |
| LMArena Math | 1499 | 1262 |
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 21% | — |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#33), Mistral Large: 30.0 (#224)
| Benchmark | GLM-5.3-Flash | Mistral Large |
|---|---|---|
| GPQA Diamond | 90.2% | 51.3% |
| LMArena Expert | 1512 | 1232 |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multimodal Not comparable
GLM-5.3-Flash: 42.6 (#25), Mistral Large: —
| Benchmark | GLM-5.3-Flash | Mistral Large |
|---|---|---|
| LMArena Vision | 1304 | — |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.2 (#24), Mistral Large: 40.1 (#214)
| Benchmark | GLM-5.3-Flash | Mistral Large |
|---|---|---|
| LMArena Non-English | 1462 | 1237 |
| LMArena Chinese | 1529 | 1240 |
| LMArena French | 1495 | 1324 |
| LMArena German | 1457 | 1254 |
| LMArena Japanese | 1420 | 1187 |
| LMArena Korean | 1443 | 1202 |
| LMArena Russian | 1472 | 1257 |
| LMArena Spanish | 1471 | 1268 |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.8 (#17), Mistral Large: 68.1 (#186)
| Benchmark | GLM-5.3-Flash | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1480 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context GLM-5.3-Flash leads
GLM-5.3-Flash: 45.3 (#41), Mistral Large: 38.3 (#194)
| Benchmark | GLM-5.3-Flash | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1479 | 1262 |
Writing & Preference GLM-5.3-Flash leads
GLM-5.3-Flash: 65.4 (#49), Mistral Large: 40.9 (#237)
| Benchmark | GLM-5.3-Flash | Mistral Large |
|---|---|---|
| LMArena Text | 1471 | 1266 |
| LMArena Creative Writing | 1440 | 1243 |
| LMArena Multi-Turn | 1471 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is GLM-5.3-Flash better than Mistral Large?
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 31.6 on the Noometry Index.
Which is cheaper, GLM-5.3-Flash or Mistral Large?
GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; Mistral Large lists at $2 and $6.
Is GLM-5.3-Flash or Mistral Large better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.7 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3-Flash does, with 1M tokens against 131K.
How many benchmarks do GLM-5.3-Flash and Mistral Large share?
23 benchmarks have published results for both models. GLM-5.3-Flash has 36 scored results on Noometry and Mistral Large has 51.