Model comparison
Gemini 3.1 Flash Lite vs GLM-5.2
GLM-5.2 is the stronger model overall, scoring 51.1 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 3.8× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Last verified . 31 shared benchmarks.
GoogleSummary
- They share 31 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 0 categories and GLM-5.2 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.2 leads 42.3 to 22.9.
- The biggest single-benchmark swing is NYT Connections (extended): 8.2% for Gemini 3.1 Flash Lite and 74.3% for GLM-5.2.
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 1M.
- GLM-5.2 has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.1 Flash Lite | GLM-5.2 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 40.8 | 51.1 |
| Released | 2026-03-03 | 2026-06-13 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 1M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.25 | $1.40 |
| Output $ / M tokens | $1.50 | $4.40 |
| Results tracked | 38 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
Gemini 3.1 Flash Lite: 37.8 (#188), GLM-5.2: 51.3 (#41)
| Benchmark | Gemini 3.1 Flash Lite | GLM-5.2 |
|---|---|---|
| LMArena WebDev | 1256 | 1603 |
| SciCode | 41.9% | 50.5% |
| WeirdML | 52.2% | 70.1% |
| LMArena Coding | 1400 | 1485 |
| ALE-Bench | 797.73 | 1,047 |
| SWE-bench Verified | — | 78.7% |
| DeepSWE | — | 43.8% |
| FrontierCode | — | 24.5% |
Agentic & Tool Use GLM-5.2 leads
Gemini 3.1 Flash Lite: 30.2 (#79), GLM-5.2: 32.4 (#63)
| Benchmark | Gemini 3.1 Flash Lite | GLM-5.2 |
|---|---|---|
| APEX-Agents | — | 45.2% |
| τ²-bench Banking | — | 37.1% |
| DeepResearch Bench | 37.3% | — |
| PostTrainBench | — | 31.7% |
| GBAEval | — | 0% |
| Vending-Bench 2 | — | 8,314 |
Reasoning GLM-5.2 leads
Gemini 3.1 Flash Lite: 22.9 (#186), GLM-5.2: 42.3 (#52)
| Benchmark | Gemini 3.1 Flash Lite | GLM-5.2 |
|---|---|---|
| Kagi LLM Benchmark | 67.2% | 62.6% |
| NYT Connections (extended) | 8.2% | 74.3% |
| CritPt | 1.1% | 20.9% |
| Chess Puzzles | 25% | 21% |
| LMArena Hard Prompts | 1407 | 1480 |
| DTBench | 76.8% | 93.6% |
| LMCA | 35% | 45.8% |
| Epoch Capabilities Index | 144.47 | 151.78 |
| ARC-AGI-2 | — | 22.8% |
| SimpleBench | — | 58.8% |
| ARC-AGI-1 | — | 77% |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 19% |
| Surface Evolver Bench | — | 55.6% |
| ForecastBench | 54.4 | — |
Math GLM-5.2 leads
Gemini 3.1 Flash Lite: 40.7 (#90), GLM-5.2: 55.7 (#43)
| Benchmark | Gemini 3.1 Flash Lite | GLM-5.2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 27.7% | 59.2% |
| OTIS Mock AIME 2024-2025 | 80% | 86.4% |
| LMArena Math | 1428 | 1482 |
| FrontierMath Tier 4 | — | 29.3% |
| MathArena Final-Answer Competitions | — | 67.6% |
| ProofBench | — | 35% |
Knowledge GLM-5.2 leads
Gemini 3.1 Flash Lite: 41.9 (#104), GLM-5.2: 57.1 (#40)
| Benchmark | Gemini 3.1 Flash Lite | GLM-5.2 |
|---|---|---|
| GPQA Diamond | 81.8% | 91.9% |
| LMArena Expert | 1398 | 1486 |
| Humanity's Last Exam | 8.6% | — |
| SimpleQA Verified | — | 34.2% |
| Vectara Hallucination Rate | 8.2% | — |
Multimodal Not comparable
Gemini 3.1 Flash Lite: 39.4 (#60), GLM-5.2: —
| Benchmark | Gemini 3.1 Flash Lite | GLM-5.2 |
|---|---|---|
| LMArena Vision | 1240 | — |
Multilingual GLM-5.2 leads
Gemini 3.1 Flash Lite: 52.3 (#86), GLM-5.2: 55.8 (#26)
| Benchmark | Gemini 3.1 Flash Lite | GLM-5.2 |
|---|---|---|
| LMArena Non-English | 1411 | 1459 |
| LMArena Chinese | 1461 | 1519 |
| LMArena French | 1424 | 1479 |
| LMArena German | 1429 | 1468 |
| LMArena Japanese | 1413 | 1451 |
| LMArena Korean | 1392 | 1445 |
| LMArena Russian | 1420 | 1466 |
| LMArena Spanish | 1421 | 1477 |
Instruction Following GLM-5.2 leads
Gemini 3.1 Flash Lite: 72.7 (#131), GLM-5.2: 76.9 (#34)
| Benchmark | Gemini 3.1 Flash Lite | GLM-5.2 |
|---|---|---|
| LMArena Instruction Following | 1377 | 1465 |
Long Context GLM-5.2 leads
Gemini 3.1 Flash Lite: 42.5 (#122), GLM-5.2: 45.3 (#43)
| Benchmark | Gemini 3.1 Flash Lite | GLM-5.2 |
|---|---|---|
| LMArena Longer Query | 1394 | 1479 |
Writing & Preference GLM-5.2 leads
Gemini 3.1 Flash Lite: 60.9 (#94), GLM-5.2: 70.4 (#21)
| Benchmark | Gemini 3.1 Flash Lite | GLM-5.2 |
|---|---|---|
| LMArena Text | 1416 | 1470 |
| LMArena Creative Writing | 1401 | 1462 |
| LMArena Multi-Turn | 1417 | 1469 |
| EQ-Bench Creative Writing | — | 1757 |
| EQ-Bench 4 | — | 1222 |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than GLM-5.2?
GLM-5.2 is the stronger model overall, scoring 51.1 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 3.8× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.1 Flash Lite or GLM-5.2?
Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.
Is Gemini 3.1 Flash Lite or GLM-5.2 better for coding?
GLM-5.2 scores higher on coding benchmarks: 51.3 versus 37.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Flash Lite does, with 1.05M tokens against 1M.
How many benchmarks do Gemini 3.1 Flash Lite and GLM-5.2 share?
31 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and GLM-5.2 has 51.