Model comparison
GLM-5.3 vs Mistral Small
GLM-5.3 is the stronger model overall, scoring 54.8 to 33.4 on the Noometry Index. Mistral Small costs 8.2× less per token, which makes it the better buy when GLM-5.3's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Mistral AISummary
- They share 24 benchmarks with published results for both. GLM-5.3 scores higher in 9 categories and Mistral Small in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.3 leads 62.3 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 91.1% for GLM-5.3 and 5.8% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.40 / $4.40 for GLM-5.3.
- GLM-5.3 accepts more context: 1M tokens versus 262K.
Side by side
| GLM-5.3 | Mistral Small | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 54.8 | 33.4 |
| Released | 2026-08-14 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 1M | 262K |
| Max output | 131K | 256K |
| Input $ / M tokens | $1.40 | $0.15 |
| Output $ / M tokens | $4.40 | $0.60 |
| Results tracked | 42 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3 leads
GLM-5.3: 59.5 (#14), Mistral Small: 34.0 (#247)
| Benchmark | GLM-5.3 | Mistral Small |
|---|---|---|
| SciCode | 59% | 26.5% |
| LMArena Coding | 1496 | 1362 |
| ALE-Bench | 1,317 | 497.62 |
| DeepSWE | 69% | — |
| FrontierCode | 40.1% | — |
| CursorBench | 42.6% | — |
| LMArena WebDev | 1622 | — |
| FrontierSWE | 30.2% | — |
| WeirdML | 75.4% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
Agentic & Tool Use GLM-5.3 leads
GLM-5.3: 36.4 (#38), Mistral Small: 28.1 (#93)
| Benchmark | GLM-5.3 | Mistral Small |
|---|---|---|
| APEX-Agents | 56.6% | — |
| Berkeley Function Calling Leaderboard | — | 37.1% |
| Vending-Bench 2 | 8,164 | — |
Reasoning GLM-5.3 leads
GLM-5.3: 46.1 (#46), Mistral Small: 19.8 (#250)
| Benchmark | GLM-5.3 | Mistral Small |
|---|---|---|
| CritPt | 19.1% | 0% |
| LMArena Hard Prompts | 1489 | 1335 |
| DTBench | 87.7% | 70.9% |
| LMCA | 55.5% | 20.6% |
| Kagi LLM Benchmark | — | 37.8% |
| NYT Connections (extended) | 74.2% | — |
| Chess Puzzles | 21% | — |
| LiveBench Reasoning | — | 44.8% |
| Mystery Game Puzzles | 33% | — |
| LiveBench Data Analysis | — | 53.7% |
| Bench to the Future 3 | 0.15 | — |
| Epoch Capabilities Index | 155.61 | — |
| LiveBench | — | 44% |
Math GLM-5.3 leads
GLM-5.3: 62.3 (#33), Mistral Small: 16.4 (#293)
| Benchmark | GLM-5.3 | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 91.1% | 5.8% |
| LMArena Math | 1489 | 1341 |
| FrontierMath (Tiers 1-3) | 68.8% | — |
| FrontierMath Tier 4 | 29.3% | — |
| ProofBench | 49% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
Knowledge GLM-5.3 leads
GLM-5.3: 58.3 (#37), Mistral Small: 31.0 (#222)
| Benchmark | GLM-5.3 | Mistral Small |
|---|---|---|
| GPQA Diamond | 90.9% | 47.5% |
| LMArena Expert | 1516 | 1291 |
| SimpleQA Verified | 41% | — |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |
Multimodal Not comparable
GLM-5.3: —, Mistral Small: 33.5 (#96)
| Benchmark | GLM-5.3 | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual GLM-5.3 leads
GLM-5.3: 55.7 (#28), Mistral Small: 45.5 (#169)
| Benchmark | GLM-5.3 | Mistral Small |
|---|---|---|
| LMArena Non-English | 1457 | 1315 |
| LMArena Chinese | 1528 | 1340 |
| LMArena French | 1499 | 1337 |
| LMArena German | 1499 | 1340 |
| LMArena Japanese | 1453 | 1275 |
| LMArena Korean | 1472 | 1259 |
| LMArena Russian | 1463 | 1324 |
| LMArena Spanish | 1460 | 1346 |
Instruction Following GLM-5.3 leads
GLM-5.3: 77.5 (#23), Mistral Small: 66.4 (#209)
| Benchmark | GLM-5.3 | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1477 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context GLM-5.3 leads
GLM-5.3: 45.4 (#41), Mistral Small: 40.4 (#156)
| Benchmark | GLM-5.3 | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1482 | 1327 |
Writing & Preference GLM-5.3 leads
GLM-5.3: 75.7 (#6), Mistral Small: 52.5 (#171)
| Benchmark | GLM-5.3 | Mistral Small |
|---|---|---|
| LMArena Text | 1471 | 1338 |
| LMArena Creative Writing | 1457 | 1305 |
| LMArena Multi-Turn | 1472 | 1344 |
| EQ-Bench Creative Writing | 2075 | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is GLM-5.3 better than Mistral Small?
GLM-5.3 is the stronger model overall, scoring 54.8 to 33.4 on the Noometry Index. Mistral Small costs 8.2× less per token, which makes it the better buy when GLM-5.3's lead doesn't matter for your workload.
Which is cheaper, GLM-5.3 or Mistral Small?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GLM-5.3 lists at $1.40 and $4.40.
Is GLM-5.3 or Mistral Small better for coding?
GLM-5.3 scores higher on coding benchmarks: 59.5 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3 does, with 1M tokens against 262K.
How many benchmarks do GLM-5.3 and Mistral Small share?
24 benchmarks have published results for both models. GLM-5.3 has 42 scored results on Noometry and Mistral Small has 39.