Model comparison
Gemini 3 Flash Preview vs GLM-5.1
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 47.8 on the Noometry Index.
Last verified . 34 shared benchmarks.
GoogleSummary
- They share 34 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 6 categories and GLM-5.1 in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Gemini 3 Flash Preview leads 38.7 to 24.9.
- The biggest single-benchmark swing is SimpleQA Verified: 66.8% for Gemini 3 Flash Preview and 34% for GLM-5.1.
- Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 200K.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| Gemini 3 Flash Preview | GLM-5.1 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 52.3 | 47.8 |
| Released | 2025-12-17 | 2026-04-07 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 200K |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.50 | $1.40 |
| Output $ / M tokens | $3 | $4.40 |
| Results tracked | 59 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 50.9 (#42), GLM-5.1: 48.7 (#55)
| Benchmark | Gemini 3 Flash Preview | GLM-5.1 |
|---|---|---|
| SWE-bench Verified | 75.4% | 74.2% |
| LMArena WebDev | 1439 | 1508 |
| WeirdML | 61.6% | 57.1% |
| LMArena Coding | 1460 | 1485 |
| ALE-Bench | 1,367 | 887.1 |
| SWE-bench Verified (bash only) | 75.8% | — |
| SWE-bench Multilingual | 72.7% | — |
| SciCode | — | 43.8% |
| GSO | 9.8% | — |
Agentic & Tool Use Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 38.7 (#29), GLM-5.1: 24.9 (#113)
| Benchmark | Gemini 3 Flash Preview | GLM-5.1 |
|---|---|---|
| Vending-Bench 2 | 3,635 | 5,634 |
| Terminal-Bench | 64.3% | — |
| APEX-Agents | — | 40.9% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| DeepResearch Bench | 49.8% | — |
| BALROG | 48.1% | — |
| ExploitBench | — | 18.1% |
| GBAEval | — | 0% |
| GDP.pdf | 10% | — |
| LMArena Search | 1198 | — |
Reasoning Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 49.2 (#37), GLM-5.1: 39.1 (#60)
| Benchmark | Gemini 3 Flash Preview | GLM-5.1 |
|---|---|---|
| SimpleBench | 61.1% | 55.1% |
| NYT Connections (extended) | 83.1% | 77.7% |
| Chess Puzzles | 40% | 19% |
| LMArena Hard Prompts | 1465 | 1472 |
| Epoch Capabilities Index | 151.8 | 149.84 |
| ARC-AGI-2 | 33.6% | — |
| ARC-AGI-1 | 84.7% | — |
| CritPt | — | 4.6% |
| Thematic Generalization | — | 69.8% |
| Mystery Game Puzzles | 26% | — |
| DTBench | 89.1% | — |
| LMCA | 43.1% | — |
| ForecastBench | 58.5 | — |
Math Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 51.7 (#55), GLM-5.1: 49.7 (#60)
| Benchmark | Gemini 3 Flash Preview | GLM-5.1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 36.8% |
| MathArena Final-Answer Competitions | 67.6% | 67.1% |
| OTIS Mock AIME 2024-2025 | 95.6% | 93.3% |
| ProofBench | 15% | 22.2% |
| LMArena Math | 1473 | 1473 |
| FrontierMath (Feb 2025 set) | 35.6% | 33.4% |
| FrontierMath Tier 4 (v1) | 4.2% | 12.5% |
| FrontierMath Tier 4 | 17.1% | — |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#33), GLM-5.1: 54.9 (#50)
| Benchmark | Gemini 3 Flash Preview | GLM-5.1 |
|---|---|---|
| GPQA Diamond | 89.4% | 89.9% |
| SimpleQA Verified | 66.8% | 34% |
| LMArena Expert | 1462 | 1476 |
| Vectara Hallucination Rate | 13.5% | — |
Multimodal Not comparable
Gemini 3 Flash Preview: 45.5 (#16), GLM-5.1: —
| Benchmark | Gemini 3 Flash Preview | GLM-5.1 |
|---|---|---|
| LMArena Vision | 1285 | — |
| GeoBench | 88% | — |
| VPCT | 72.6% | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1413 | — |
Multilingual Too close to call
Gemini 3 Flash Preview: 55.7 (#27), GLM-5.1: 55.0 (#36)
| Benchmark | Gemini 3 Flash Preview | GLM-5.1 |
|---|---|---|
| LMArena Non-English | 1458 | 1447 |
| LMArena Chinese | 1511 | 1515 |
| LMArena French | 1477 | 1474 |
| LMArena German | 1497 | 1465 |
| LMArena Japanese | 1489 | 1434 |
| LMArena Korean | 1443 | 1418 |
| LMArena Russian | 1480 | 1454 |
| LMArena Spanish | 1469 | 1469 |
Instruction Following Too close to call
Gemini 3 Flash Preview: 75.7 (#56), GLM-5.1: 76.3 (#42)
| Benchmark | Gemini 3 Flash Preview | GLM-5.1 |
|---|---|---|
| LMArena Instruction Following | 1437 | 1451 |
Long Context Too close to call
Gemini 3 Flash Preview: 44.4 (#67), GLM-5.1: 44.9 (#53)
| Benchmark | Gemini 3 Flash Preview | GLM-5.1 |
|---|---|---|
| LMArena Longer Query | 1452 | 1466 |
Writing & Preference GLM-5.1 leads
Gemini 3 Flash Preview: 65.5 (#45), GLM-5.1: 66.9 (#31)
| Benchmark | Gemini 3 Flash Preview | GLM-5.1 |
|---|---|---|
| LMArena Text | 1466 | 1461 |
| LMArena Creative Writing | 1457 | 1453 |
| LMArena Multi-Turn | 1471 | 1472 |
| EQ-Bench Creative Writing | — | 1592 |
Frequently asked questions
Is Gemini 3 Flash Preview better than GLM-5.1?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 47.8 on the Noometry Index.
Which is cheaper, Gemini 3 Flash Preview or GLM-5.1?
Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is Gemini 3 Flash Preview or GLM-5.1 better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 48.7 in the Noometry coding category.
Which has the bigger context window?
Gemini 3 Flash Preview does, with 1.05M tokens against 200K.
How many benchmarks do Gemini 3 Flash Preview and GLM-5.1 share?
34 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and GLM-5.1 has 41.