Model comparison
GLM-5.1 vs GPT-5 Mini
GLM-5.1 is the stronger model overall, scoring 47.8 to 41.8 on the Noometry Index. GPT-5 Mini costs 3.1× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and GPT-5 Mini in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 39.1 to 23.9.
- The biggest single-benchmark swing is GPQA Diamond: 89.9% for GLM-5.1 and 75% for GPT-5 Mini.
- GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GPT-5 Mini accepts more context: 400K tokens versus 200K.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.1 | GPT-5 Mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 47.8 | 41.8 |
| Released | 2026-04-07 | 2025-08-07 |
| Weights | Open | Proprietary |
| Context window | 200K | 400K |
| Max output | 131K | 128K |
| Input $ / M tokens | $1.40 | $0.25 |
| Output $ / M tokens | $4.40 | $2 |
| Results tracked | 41 | 60 |
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), GPT-5 Mini: 40.1 (#146)
| Benchmark | GLM-5.1 | GPT-5 Mini |
|---|---|---|
| SWE-bench Verified | 74.2% | 64.7% |
| SciCode | 43.8% | 39.2% |
| WeirdML | 57.1% | 52.7% |
| LMArena Coding | 1485 | 1406 |
| ALE-Bench | 887.1 | 799.77 |
| SWE-bench Verified (bash only) | — | 59.8% |
| LMArena WebDev | 1508 | — |
| SWE-bench Multilingual | — | 39.7% |
| AlgoTune | — | 1.38 |
Agentic & Tool Use GPT-5 Mini leads
GLM-5.1: 24.9 (#113), GPT-5 Mini: 31.1 (#70)
| Benchmark | GLM-5.1 | GPT-5 Mini |
|---|---|---|
| Vending-Bench 2 | 5,634 | -31.18 |
| Terminal-Bench | — | 34.8% |
| APEX-Agents | 40.9% | — |
| Berkeley Function Calling Leaderboard | — | 55.5% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), GPT-5 Mini: 23.9 (#168)
| Benchmark | GLM-5.1 | GPT-5 Mini |
|---|---|---|
| CritPt | 4.6% | 0% |
| Chess Puzzles | 19% | 30% |
| LMArena Hard Prompts | 1472 | 1380 |
| Epoch Capabilities Index | 149.84 | 145.52 |
| ARC-AGI-2 | — | 4.4% |
| SimpleBench | 55.1% | — |
| Kagi LLM Benchmark | — | 70.3% |
| NYT Connections (extended) | 77.7% | — |
| ARC-AGI-1 | — | 54.3% |
| EnigmaEval | — | 8.2% |
| Thematic Generalization | 69.8% | — |
| Mystery Game Puzzles | — | 10% |
| DTBench | — | 80.5% |
| LMCA | — | 34.2% |
| ForecastBench | — | 61 |
Math GLM-5.1 leads
GLM-5.1: 49.7 (#60), GPT-5 Mini: 46.7 (#69)
| Benchmark | GLM-5.1 | GPT-5 Mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 46.7% |
| OTIS Mock AIME 2024-2025 | 93.3% | 86.7% |
| ProofBench | 22.2% | 9% |
| LMArena Math | 1473 | 1378 |
| FrontierMath (Feb 2025 set) | 33.4% | 27.2% |
| FrontierMath Tier 4 (v1) | 12.5% | 6.3% |
| FrontierMath Tier 4 | — | 12.2% |
| MathArena Final-Answer Competitions | 67.1% | — |
| Omni-MATH | — | 72.2% |
| MATH Level 5 | — | 97.8% |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), GPT-5 Mini: 45.6 (#86)
| Benchmark | GLM-5.1 | GPT-5 Mini |
|---|---|---|
| GPQA Diamond | 89.9% | 75% |
| SimpleQA Verified | 34% | 21.6% |
| LMArena Expert | 1476 | 1379 |
| Humanity's Last Exam | — | 19.4% |
| MMLU-Pro | — | 83.5% |
| Confabulations | — | 13.3% |
| Vectara Hallucination Rate | — | 12.9% |
| GPQA (HELM) | — | 75.6% |
Multimodal Not comparable
GLM-5.1: —, GPT-5 Mini: 35.6 (#85)
| Benchmark | GLM-5.1 | GPT-5 Mini |
|---|---|---|
| LMArena Vision | — | 1202 |
| VPCT | — | 40.2% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), GPT-5 Mini: 48.9 (#137)
| Benchmark | GLM-5.1 | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1447 | 1363 |
| LMArena Chinese | 1515 | 1385 |
| LMArena French | 1474 | 1386 |
| LMArena German | 1465 | 1366 |
| LMArena Japanese | 1434 | 1341 |
| LMArena Korean | 1418 | 1308 |
| LMArena Russian | 1454 | 1362 |
| LMArena Spanish | 1469 | 1355 |
Instruction Following Too close to call
GLM-5.1: 76.3 (#42), GPT-5 Mini: 76.2 (#46)
| Benchmark | GLM-5.1 | GPT-5 Mini |
|---|---|---|
| LMArena Instruction Following | 1451 | 1357 |
| IFEval | — | 92.7% |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#53), GPT-5 Mini: 41.9 (#132)
| Benchmark | GLM-5.1 | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1466 | 1355 |
| Fiction.LiveBench | — | 69.4% |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), GPT-5 Mini: 55.2 (#148)
| Benchmark | GLM-5.1 | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1461 | 1373 |
| LMArena Creative Writing | 1453 | 1325 |
| EQ-Bench Creative Writing | 1592 | 1313 |
| LMArena Multi-Turn | 1472 | 1363 |
| Short-Story Creative Writing | — | 83.1% |
| WildBench | — | 85.5% |
Frequently asked questions
Is GLM-5.1 better than GPT-5 Mini?
GLM-5.1 is the stronger model overall, scoring 47.8 to 41.8 on the Noometry Index. GPT-5 Mini costs 3.1× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Which is cheaper, GLM-5.1 or GPT-5 Mini?
GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or GPT-5 Mini better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Mini does, with 400K tokens against 200K.
How many benchmarks do GLM-5.1 and GPT-5 Mini share?
33 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and GPT-5 Mini has 60.