Model comparison
GLM-5.1 vs o3
GLM-5.1 and o3 score almost the same on the Noometry Index (47.8 vs 47.5), so choose on price, context window or the category you care about most.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. GLM-5.1 scores higher in 6 categories and o3 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where o3 leads 34.5 to 24.9.
- The biggest single-benchmark swing is Chess Puzzles: 19% for GLM-5.1 and 38% for o3.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $2 / $8 for o3.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.1 | o3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 47.8 | 47.5 |
| Released | 2026-04-07 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 200K | 200K |
| Max output | 131K | 100K |
| Input $ / M tokens | $1.40 | $2 |
| Output $ / M tokens | $4.40 | $8 |
| Results tracked | 41 | 63 |
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), o3: 46.8 (#64)
| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| SWE-bench Verified | 74.2% | 62.3% |
| WeirdML | 57.1% | 52.4% |
| LMArena Coding | 1485 | 1408 |
| ALE-Bench | 887.1 | 933.55 |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| LMArena WebDev | 1508 | — |
| SciCode | 43.8% | — |
| GSO | — | 8.8% |
| CadEval | — | 74% |
Agentic & Tool Use o3 leads
GLM-5.1: 24.9 (#113), o3: 34.5 (#44)
| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| APEX-Agents | 40.9% | — |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), o3: 32.0 (#78)
| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| SimpleBench | 55.1% | 53.1% |
| CritPt | 4.6% | 1.4% |
| Chess Puzzles | 19% | 38% |
| LMArena Hard Prompts | 1472 | 1402 |
| Epoch Capabilities Index | 149.84 | 146.86 |
| ARC-AGI-2 | — | 6.5% |
| Kagi LLM Benchmark | — | 67.6% |
| NYT Connections (extended) | 77.7% | — |
| ARC-AGI-1 | — | 60.8% |
| EnigmaEval | — | 13.1% |
| Thematic Generalization | 69.8% | — |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 84.8% |
| LMCA | — | 39.7% |
| ForecastBench | — | 62.5 |
Math Too close to call
GLM-5.1: 49.7 (#60), o3: 50.2 (#58)
| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 33.3% |
| OTIS Mock AIME 2024-2025 | 93.3% | 84.4% |
| LMArena Math | 1473 | 1426 |
| FrontierMath (Feb 2025 set) | 33.4% | 18.7% |
| FrontierMath Tier 4 (v1) | 12.5% | 2.1% |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| Omni-MATH | — | 71.4% |
| MATH Level 5 | — | 97.8% |
Knowledge Too close to call
GLM-5.1: 54.9 (#50), o3: 54.6 (#52)
| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| GPQA Diamond | 89.9% | 81.8% |
| SimpleQA Verified | 34% | 49.4% |
| LMArena Expert | 1476 | 1402 |
| Humanity's Last Exam | — | 20.3% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |
Multimodal Not comparable
GLM-5.1: —, o3: 41.4 (#36)
| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), o3: 51.7 (#105)
| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| LMArena Non-English | 1447 | 1401 |
| LMArena Chinese | 1515 | 1437 |
| LMArena French | 1474 | 1430 |
| LMArena German | 1465 | 1420 |
| LMArena Japanese | 1434 | 1403 |
| LMArena Korean | 1418 | 1370 |
| LMArena Russian | 1454 | 1406 |
| LMArena Spanish | 1469 | 1395 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), o3: 72.8 (#127)
| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| LMArena Instruction Following | 1451 | 1368 |
| IFEval | — | 86.9% |
Long Context o3 leads
GLM-5.1: 44.9 (#53), o3: 53.3 (#6)
| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| LMArena Longer Query | 1466 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), o3: 63.5 (#64)
| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| LMArena Text | 1461 | 1410 |
| LMArena Creative Writing | 1453 | 1359 |
| EQ-Bench Creative Writing | 1592 | 1676 |
| LMArena Multi-Turn | 1472 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| WildBench | — | 86.1% |
Frequently asked questions
Is GLM-5.1 better than o3?
GLM-5.1 and o3 score almost the same on the Noometry Index (47.8 vs 47.5), so choose on price, context window or the category you care about most.
Which is cheaper, GLM-5.1 or o3?
GLM-5.1 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; o3 lists at $2 and $8.
Is GLM-5.1 or o3 better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 46.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do GLM-5.1 and o3 share?
31 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and o3 has 63.