Model comparison
GLM-5.1 vs GPT-4o mini
GLM-5.1 is the stronger model overall, scoring 47.8 to 25.5 on the Noometry Index. GPT-4o mini costs 8.2× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and GPT-4o mini in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.1 leads 49.7 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 6.9% for GPT-4o mini.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5.1 accepts more context: 200K tokens versus 128K.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.1 | GPT-4o mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 47.8 | 25.5 |
| Released | 2026-04-07 | 2024-07-18 |
| Weights | Open | Proprietary |
| Context window | 200K | 128K |
| Max output | 131K | 16K |
| Input $ / M tokens | $1.40 | $0.15 |
| Output $ / M tokens | $4.40 | $0.60 |
| 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-4o mini: 22.0 (#335)
| Benchmark | GLM-5.1 | GPT-4o mini |
|---|---|---|
| WeirdML | 57.1% | 11.8% |
| LMArena Coding | 1485 | 1290 |
| SWE-bench Verified | 74.2% | — |
| Aider Polyglot | — | 3.6% |
| LMArena WebDev | 1508 | — |
| SciCode | 43.8% | — |
| BigCodeBench Instruct | — | 46.1% |
| LiveBench Coding | — | 43.1% |
| BigCodeBench Complete | — | 57.4% |
| ALE-Bench | 887.1 | — |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |
Agentic & Tool Use GPT-4o mini leads
GLM-5.1: 24.9 (#113), GPT-4o mini: 27.5 (#101)
| Benchmark | GLM-5.1 | GPT-4o mini |
|---|---|---|
| APEX-Agents | 40.9% | — |
| BALROG | — | 17.4% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), GPT-4o mini: 8.7 (#347)
| Benchmark | GLM-5.1 | GPT-4o mini |
|---|---|---|
| SimpleBench | 55.1% | 10.7% |
| Chess Puzzles | 19% | 0% |
| LMArena Hard Prompts | 1472 | 1267 |
| Epoch Capabilities Index | 149.84 | 126.56 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 28.8% |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Thematic Generalization | 69.8% | — |
| LiveBench Reasoning | — | 32.8% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 54.4% |
| LiveBench Data Analysis | — | 50% |
| LMCA | — | 10.4% |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |
Math GLM-5.1 leads
GLM-5.1: 49.7 (#60), GPT-4o mini: 10.4 (#314)
| Benchmark | GLM-5.1 | GPT-4o mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 0.7% |
| OTIS Mock AIME 2024-2025 | 93.3% | 6.9% |
| LMArena Math | 1473 | 1267 |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| Omni-MATH | — | 28% |
| LiveBench Math | — | 36.3% |
| MATH Level 5 | — | 52.6% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
| GSM8K | — | 91.3% |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), GPT-4o mini: 17.7 (#284)
| Benchmark | GLM-5.1 | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 89.9% | 37.7% |
| SimpleQA Verified | 34% | 8.3% |
| LMArena Expert | 1476 | 1235 |
| MMLU-Pro | — | 60.3% |
| Confabulations | — | 37.2% |
| GPQA (HELM) | — | 36.8% |
| BoolQ | — | 88.7% |
| MMLU | — | 81.8% |
Multimodal Not comparable
GLM-5.1: —, GPT-4o mini: 25.9 (#122)
| Benchmark | GLM-5.1 | GPT-4o mini |
|---|---|---|
| LMArena Vision | — | 1066 |
| Video-MME | — | 64.8% |
| GeoBench | — | 64% |
| VPCT | — | 34% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), GPT-4o mini: 42.0 (#199)
| Benchmark | GLM-5.1 | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1447 | 1266 |
| LMArena Chinese | 1515 | 1265 |
| LMArena French | 1474 | 1297 |
| LMArena German | 1465 | 1272 |
| LMArena Japanese | 1434 | 1216 |
| LMArena Korean | 1418 | 1195 |
| LMArena Russian | 1454 | 1275 |
| LMArena Spanish | 1469 | 1276 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), GPT-4o mini: 61.9 (#239)
| Benchmark | GLM-5.1 | GPT-4o mini |
|---|---|---|
| LMArena Instruction Following | 1451 | 1258 |
| LiveBench Instruction Following | — | 56.8% |
| IFEval | — | 78.2% |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#53), GPT-4o mini: 39.1 (#186)
| Benchmark | GLM-5.1 | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1466 | 1289 |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), GPT-4o mini: 39.5 (#248)
| Benchmark | GLM-5.1 | GPT-4o mini |
|---|---|---|
| LMArena Text | 1461 | 1286 |
| LMArena Creative Writing | 1453 | 1268 |
| EQ-Bench Creative Writing | 1592 | 873 |
| LMArena Multi-Turn | 1472 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| WildBench | — | 79.1% |
| LiveBench Language | — | 28.6% |
Frequently asked questions
Is GLM-5.1 better than GPT-4o mini?
GLM-5.1 is the stronger model overall, scoring 47.8 to 25.5 on the Noometry Index. GPT-4o mini costs 8.2× 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-4o mini?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or GPT-4o mini better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
GLM-5.1 does, with 200K tokens against 128K.
How many benchmarks do GLM-5.1 and GPT-4o mini share?
26 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and GPT-4o mini has 60.