Model comparison
Gemini 2.5 Flash-Lite vs GLM-4.7
GLM-4.7 is the stronger model overall, scoring 42.0 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 5.7× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
GoogleSummary
- They share 20 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 1 category and GLM-4.7 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 32.5.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 3.3% for Gemini 2.5 Flash-Lite and 11.7% for GLM-4.7.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 205K.
- GLM-4.7 has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash-Lite | GLM-4.7 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 37.0 | 42.0 |
| Released | 2025-06-17 | 2025-12-22 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 205K |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.10 | $0.60 |
| Output $ / M tokens | $0.40 | $2.20 |
| Results tracked | 33 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
Gemini 2.5 Flash-Lite: 38.5 (#173), GLM-4.7: 44.0 (#79)
| Benchmark | Gemini 2.5 Flash-Lite | GLM-4.7 |
|---|---|---|
| LMArena Coding | 1373 | 1454 |
| ALE-Bench | 325.9 | 399.48 |
| LMArena WebDev | — | 1435 |
| SciCode | — | 45.1% |
| WeirdML | 35.2% | — |
Agentic & Tool Use Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 28.0 (#96), GLM-4.7: 26.5 (#103)
| Benchmark | Gemini 2.5 Flash-Lite | GLM-4.7 |
|---|---|---|
| Terminal-Bench | — | 33.4% |
| Berkeley Function Calling Leaderboard | 36.9% | — |
| Vending-Bench 2 | — | 2,377 |
Reasoning GLM-4.7 leads
Gemini 2.5 Flash-Lite: 22.2 (#205), GLM-4.7: 24.3 (#164)
| Benchmark | Gemini 2.5 Flash-Lite | GLM-4.7 |
|---|---|---|
| LMArena Hard Prompts | 1377 | 1443 |
| Epoch Capabilities Index | 133.94 | 143.51 |
| SimpleBench | — | 47.7% |
| Kagi LLM Benchmark | 40.5% | — |
| CritPt | — | 1.7% |
| Chess Puzzles | — | 6% |
| DTBench | 62.8% | — |
| LMCA | 18.1% | — |
Math Too close to call
Gemini 2.5 Flash-Lite: 38.0 (#144), GLM-4.7: 38.6 (#135)
| Benchmark | Gemini 2.5 Flash-Lite | GLM-4.7 |
|---|---|---|
| LMArena Math | 1373 | 1423 |
| OTIS Mock AIME 2024-2025 | — | 83.3% |
| ProofBench | — | 6% |
| Omni-MATH | 48% | — |
| FrontierMath (Feb 2025 set) | — | 2.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge GLM-4.7 leads
Gemini 2.5 Flash-Lite: 32.5 (#210), GLM-4.7: 47.0 (#80)
| Benchmark | Gemini 2.5 Flash-Lite | GLM-4.7 |
|---|---|---|
| Vectara Hallucination Rate | 3.3% | 11.7% |
| LMArena Expert | 1373 | 1424 |
| GPQA Diamond | — | 83.3% |
| SimpleQA Verified | — | 32.2% |
| MMLU-Pro | 53.7% | — |
| GPQA (HELM) | 30.9% | — |
Multimodal Not comparable
Gemini 2.5 Flash-Lite: 29.1 (#114), GLM-4.7: —
| Benchmark | Gemini 2.5 Flash-Lite | GLM-4.7 |
|---|---|---|
| LMArena Vision | 1198 | — |
| VPCT | 30% | — |
Multilingual GLM-4.7 leads
Gemini 2.5 Flash-Lite: 49.3 (#134), GLM-4.7: 52.8 (#79)
| Benchmark | Gemini 2.5 Flash-Lite | GLM-4.7 |
|---|---|---|
| LMArena Non-English | 1369 | 1417 |
| LMArena Chinese | 1404 | 1495 |
| LMArena French | 1388 | 1432 |
| LMArena German | 1389 | 1424 |
| LMArena Japanese | 1359 | 1439 |
| LMArena Korean | 1360 | 1399 |
| LMArena Russian | 1373 | 1423 |
| LMArena Spanish | 1396 | 1434 |
Instruction Following GLM-4.7 leads
Gemini 2.5 Flash-Lite: 70.0 (#168), GLM-4.7: 74.4 (#95)
| Benchmark | Gemini 2.5 Flash-Lite | GLM-4.7 |
|---|---|---|
| LMArena Instruction Following | 1367 | 1411 |
| IFEval | 81% | — |
Long Context GLM-4.7 leads
Gemini 2.5 Flash-Lite: 33.3 (#262), GLM-4.7: 42.8 (#116)
| Benchmark | Gemini 2.5 Flash-Lite | GLM-4.7 |
|---|---|---|
| LMArena Longer Query | 1373 | 1432 |
| Fiction.LiveBench | 47.2% | — |
| CL-bench | — | 15.9% |
| CL-bench Life | — | 10.9% |
Writing & Preference GLM-4.7 leads
Gemini 2.5 Flash-Lite: 56.8 (#135), GLM-4.7: 60.9 (#93)
| Benchmark | Gemini 2.5 Flash-Lite | GLM-4.7 |
|---|---|---|
| LMArena Text | 1379 | 1435 |
| LMArena Creative Writing | 1367 | 1401 |
| LMArena Multi-Turn | 1366 | 1446 |
| EQ-Bench Creative Writing | — | 1413 |
| WildBench | 81.8% | — |
Frequently asked questions
Is Gemini 2.5 Flash-Lite better than GLM-4.7?
GLM-4.7 is the stronger model overall, scoring 42.0 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 5.7× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Flash-Lite or GLM-4.7?
Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.
Is Gemini 2.5 Flash-Lite or GLM-4.7 better for coding?
GLM-4.7 scores higher on coding benchmarks: 44.0 versus 38.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash-Lite does, with 1.05M tokens against 205K.
How many benchmarks do Gemini 2.5 Flash-Lite and GLM-4.7 share?
20 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and GLM-4.7 has 36.