Model comparison
GLM-5 vs GPT-4.1 mini
GLM-5 is the stronger model overall, scoring 46.1 to 33.6 on the Noometry Index. GPT-4.1 mini costs 2.2× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Last verified . 28 shared benchmarks.
Summary
- They share 28 benchmarks with published results for both. GLM-5 scores higher in 8 categories and GPT-4.1 mini in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5 leads 46.4 to 24.1.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 72.8% for GLM-5 and 23.9% for GPT-4.1 mini.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $1 / $3.20 for GLM-5.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 205K.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| GLM-5 | GPT-4.1 mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 46.1 | 33.6 |
| Released | 2026-02-11 | 2025-04-14 |
| Weights | Open | Proprietary |
| Context window | 205K | 1.05M |
| Max output | 131K | 33K |
| Input $ / M tokens | $1 | $0.40 |
| Output $ / M tokens | $3.20 | $1.60 |
| Results tracked | 45 | 47 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), GPT-4.1 mini: 30.6 (#293)
| Benchmark | GLM-5 | GPT-4.1 mini |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | 23.9% |
| WeirdML | 48.2% | 37.6% |
| LMArena Coding | 1461 | 1367 |
| SWE-bench Verified | 72.1% | — |
| Aider Polyglot | — | 32.4% |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| SciCode | — | 40.4% |
| BigCodeBench Instruct | — | 48.9% |
| CadEval | — | 16% |
| ALE-Bench | 765.62 | — |
Agentic & Tool Use GPT-4.1 mini leads
GLM-5: 31.1 (#71), GPT-4.1 mini: 33.3 (#55)
| Benchmark | GLM-5 | GPT-4.1 mini |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| Berkeley Function Calling Leaderboard | — | 50.5% |
| 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), GPT-4.1 mini: 10.8 (#340)
| Benchmark | GLM-5 | GPT-4.1 mini |
|---|---|---|
| ARC-AGI-2 | 4.9% | 0% |
| Kagi LLM Benchmark | 75% | 48.6% |
| ARC-AGI-1 | 44.7% | 3.5% |
| Chess Puzzles | 10% | 7% |
| LMArena Hard Prompts | 1452 | 1349 |
| Epoch Capabilities Index | 145.83 | 135.01 |
| SimpleBench | 53.2% | — |
| NYT Connections (extended) | 74.8% | — |
| CritPt | — | 0% |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LMCA | — | 21.1% |
| ForecastBench | 61 | — |
Math GLM-5 leads
GLM-5: 46.4 (#71), GPT-4.1 mini: 24.1 (#270)
| Benchmark | GLM-5 | GPT-4.1 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 44.7% |
| LMArena Math | 1440 | 1343 |
| FrontierMath (Feb 2025 set) | 16.4% | 4.5% |
| FrontierMath (Tiers 1-3) | — | 6.7% |
| MathArena Final-Answer Competitions | 65.7% | — |
| Omni-MATH | — | 49.1% |
| MATH Level 5 | — | 87.3% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), GPT-4.1 mini: 34.7 (#194)
| Benchmark | GLM-5 | GPT-4.1 mini |
|---|---|---|
| GPQA Diamond | 87.8% | 65.8% |
| LMArena Expert | 1454 | 1338 |
| SimpleQA Verified | — | 12.7% |
| MMLU-Pro | — | 78.3% |
| Vectara Hallucination Rate | 10.1% | — |
| GPQA (HELM) | — | 61.4% |
Multimodal Not comparable
GLM-5: —, GPT-4.1 mini: 35.8 (#82)
| Benchmark | GLM-5 | GPT-4.1 mini |
|---|---|---|
| LMArena Vision | — | 1181 |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), GPT-4.1 mini: 45.7 (#166)
| Benchmark | GLM-5 | GPT-4.1 mini |
|---|---|---|
| LMArena Non-English | 1430 | 1318 |
| LMArena Chinese | 1511 | 1329 |
| LMArena French | 1455 | 1358 |
| LMArena German | 1445 | 1351 |
| LMArena Japanese | 1416 | 1290 |
| LMArena Korean | 1423 | 1298 |
| LMArena Russian | 1436 | 1324 |
| LMArena Spanish | 1454 | 1319 |
Instruction Following GLM-5 leads
GLM-5: 75.2 (#67), GPT-4.1 mini: 73.7 (#118)
| Benchmark | GLM-5 | GPT-4.1 mini |
|---|---|---|
| LMArena Instruction Following | 1428 | 1333 |
| IFEval | — | 90.4% |
Long Context GLM-5 leads
GLM-5: 44.7 (#60), GPT-4.1 mini: 31.8 (#275)
| Benchmark | GLM-5 | GPT-4.1 mini |
|---|---|---|
| LMArena Longer Query | 1446 | 1344 |
| Fiction.LiveBench | — | 44.4% |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), GPT-4.1 mini: 48.6 (#199)
| Benchmark | GLM-5 | GPT-4.1 mini |
|---|---|---|
| LMArena Text | 1446 | 1340 |
| LMArena Creative Writing | 1439 | 1300 |
| EQ-Bench Creative Writing | 1601 | 1147 |
| LMArena Multi-Turn | 1456 | 1354 |
| WildBench | — | 83.8% |
Frequently asked questions
Is GLM-5 better than GPT-4.1 mini?
GLM-5 is the stronger model overall, scoring 46.1 to 33.6 on the Noometry Index. GPT-4.1 mini costs 2.2× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Which is cheaper, GLM-5 or GPT-4.1 mini?
GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; GLM-5 lists at $1 and $3.20.
Is GLM-5 or GPT-4.1 mini better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 30.6 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 mini does, with 1.05M tokens against 205K.
How many benchmarks do GLM-5 and GPT-4.1 mini share?
28 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and GPT-4.1 mini has 47.