Gemini 3 Flash Preview vs GLM 5.2
GLM 5.2 leads Gemini 3 Flash Preview on coding, 61.1 to 43.7 on the Vibe Coding Index, and Gemini 3 Flash Preview costs 1.5x less per output token ($3.00 vs $4.40 per million). Updated October 22, 2026; 49 benchmarks have a result for both.
Gemini 3 Flash Preview or GLM 5.2: which to pick
Pick GLM 5.2 for coding: it scores 61.1 on the Vibe Coding Index against 43.7 for Gemini 3 Flash Preview.
Pick Gemini 3 Flash Preview for output tokens 1.5x cheaper ($3.00 vs $4.40 per million) and a lower cost per solved task ($0.37 against $0.86).
- Shared results
- 49
- Gemini 3 Flash Preview only
- 22
- GLM 5.2 only
- 49
- Like-for-like categories
- 8 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
GLM 5.2
GLM 5.2 scores 61.1 against 43.7.
2 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
GLM 5.2
GLM 5.2 leads, 33.7 against 26.3.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only GLM 5.2 has a AA Agentic Index result, 38.4.
Directional only
Reasoning
GPQA Diamond
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 87.9% against 85.6%.
Same board, both measured
Math
AIME
No call
Only Gemini 3 Flash Preview has a AIME result, 95.6%.
Directional only
Knowledge
MMLU Pro
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 88.6% against 86.7%.
Same board, both measured
Web design
Design Arena: websites
GLM 5.2
GLM 5.2 leads, 1285 against 1196.
Same board, both measured
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemini 3 Flash Preview
Gemini 3 Flash Preview $0.0020, GLM 5.2 $0.0036 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Gemini 3 Flash Preview
Gemini 3 Flash Preview $0.37, GLM 5.2 $0.86.
Published attempt cost and pass rate
At a glance
- Coding index
- Gemini 3 Flash Preview 43.7 from 2 benchmarks, GLM 5.2 61.1 from 4 benchmarks.
- Widest category
- Agentic work, 16.7 points apart on average over 11 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): Gemini 3 Flash Preview 20.2% against GLM 5.2 64.0%, 43.8 points apart on a 0 to 100 scale.
- Output price
- Gemini 3 Flash Preview $3.00 against GLM 5.2 $4.40 per million output tokens, 1.5x apart.
- Context window
- Both take 1.05M tokens.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Gemini 3 Flash Preview | Bars | GLM 5.2 | Ties |
|---|---|---|---|---|
| Coding | 2 | 7 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 1 | 10 | ||
| Reasoning | 7 | 2 | ||
| Math | 1 | 3 | ||
| Knowledge | 6 | 0 | ||
| Web design | 0 | 4 | ||
| General | 1 | 4 | ||
| All shared boards | 18 | 31 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index27
| Benchmark | Gemini 3 Flash Preview | GLM 5.2 | Leader |
|---|---|---|---|
| SWE-bench Verified | 75.8% | Not measured | Only Gemini 3 Flash Preview measured |
| LMArena WebDev | Not measured | 1604 | Only GLM 5.2 measured |
| AA Coding Index | Not measured | 68.8 | Only GLM 5.2 measured |
| LiveCodeBench (Vals AI) | 85.6% | 69.5% | Gemini 3 Flash Preview |
| SWE-bench Verified (Vals AI) | 75.0% | 82.8% | GLM 5.2 |
| Vibe Code Bench (Vals AI) | 20.2% | 64.0% | GLM 5.2 |
| Code migration (Vals AI) | 6.4% | 37.9% | GLM 5.2 |
| ProgramBench (Vals AI) | 0.0% | 0.5% | GLM 5.2 |
| Terminal-Bench 2.1 (Vals AI) | 53.9% | 67.8% | GLM 5.2 |
| SkillsBench (Vals AI) | Not measured | 45.1% | Only GLM 5.2 measured |
| LiveCodeBench (Artificial Analysis run) | 90.8% | Not measured | Only Gemini 3 Flash Preview measured |
| SciCode | Not measured | 51.2% | Only GLM 5.2 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 38.6% | 50.8% | GLM 5.2 |
| Terminal-Bench | 64.3% | Not measured | Only Gemini 3 Flash Preview measured |
| FrontierCode | Not measured | 24.5% | Only GLM 5.2 measured |
| GSO-Bench | 9.8% | Not measured | Only Gemini 3 Flash Preview measured |
| WeirdML | 61.6% | 70.1% | GLM 5.2 |
| ALE-Bench | 1367.2 | 1047.0 | Gemini 3 Flash Preview |
| LMArena Text: coding | Not measured | 1487 | Only GLM 5.2 measured |
| LMArena Text: software and IT | Not measured | 1486 | Only GLM 5.2 measured |
| LMArena WebDev: React | Not measured | 1617 | Only GLM 5.2 measured |
| LMArena WebDev: HTML | Not measured | 1565 | Only GLM 5.2 measured |
| SciCode | 12.7% | Not measured | Only Gemini 3 Flash Preview measured |
| Neither model has a result on the other 16 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemini 3 Flash Preview | GLM 5.2 | Leader |
|---|---|---|---|
| AA Intelligence Index | 26.3 | 33.7 | GLM 5.2 |
| Epoch Capabilities Index | Not measured | 151.9 | Only GLM 5.2 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index110
| Benchmark | Gemini 3 Flash Preview | GLM 5.2 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 38.4 | Only GLM 5.2 measured |
| Design Arena: agents building web apps | 1111 | 1222 | GLM 5.2 |
| Design Arena: agents building full-stack apps | 1063 | 1241 | GLM 5.2 |
| Design Arena: agents building mobile apps | 1090 | 1159 | GLM 5.2 |
| Design Arena: agents building Android apps | 1051 | 1178 | GLM 5.2 |
| Design Arena: agents building Godot games | 1161 | 1142 | Gemini 3 Flash Preview |
| Design Arena: agents building games | Not measured | 1206 | Only GLM 5.2 measured |
| Design Arena: HTML slides | Not measured | 1125 | Only GLM 5.2 measured |
| Design Arena: PowerPoint slides | 1036 | 1170 | GLM 5.2 |
| SREBench (Vals AI) | Not measured | 0.0% | Only GLM 5.2 measured |
| Finance Agent (Vals AI) | 42.5% | 49.7% | GLM 5.2 |
| Tax Agent Bench (Vals AI) | 11.8% | Not measured | Only Gemini 3 Flash Preview measured |
| Legal Research Bench (Vals AI) | 18.3% | 31.3% | GLM 5.2 |
| Excel Modeling Benchmark (Vals AI) | 26.0% | 61.5% | GLM 5.2 |
| τ²-Bench Telecom | 80.4% | 99.1% | GLM 5.2 |
| APEX-Agents | Not measured | 45.2% | Only GLM 5.2 measured |
| BALROG | 48.1% | Not measured | Only Gemini 3 Flash Preview measured |
| DeepResearch Bench | 49.8% | Not measured | Only Gemini 3 Flash Preview measured |
| PostTrainBench | Not measured | 31.7% | Only GLM 5.2 measured |
| Vending-Bench 2 | $3,635 | $8,314 | GLM 5.2 |
| Neither model has a result on the other 21 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index72
| Benchmark | Gemini 3 Flash Preview | GLM 5.2 | Leader |
|---|---|---|---|
| GPQA Diamond | 87.9% | 85.6% | Gemini 3 Flash Preview |
| MMMU Pro (Vals AI) | 87.6% | Not measured | Only Gemini 3 Flash Preview measured |
| GPQA Diamond (Artificial Analysis run) | 89.8% | 89.5% | Gemini 3 Flash Preview |
| Humanity's Last Exam (Artificial Analysis run) | 36.6% | 41.1% | GLM 5.2 |
| GPQA Diamond (Epoch AI run) | 89.4% | 91.9% | GLM 5.2 |
| ARC-AGI | 84.7% | 77.0% | Gemini 3 Flash Preview |
| ARC-AGI-2 | 33.6% | 22.8% | Gemini 3 Flash Preview |
| SimpleBench | 61.1% | 58.8% | Gemini 3 Flash Preview |
| Chess puzzles | 39.0% | 22.0% | Gemini 3 Flash Preview |
| Mystery game puzzles | 26.0% | 19.0% | Gemini 3 Flash Preview |
| EBR-bench | Not measured | 9.5% | Only GLM 5.2 measured |
| VPCT | 72.6% | Not measured | Only Gemini 3 Flash Preview measured |
| LMArena Text: hard prompts | Not measured | 1481 | Only GLM 5.2 measured |
| LMArena Text: expert | Not measured | 1487 | Only GLM 5.2 measured |
| LMArena Text: hard prompts in English | Not measured | 1481 | Only GLM 5.2 measured |
| Kagi LLM Benchmark | Not measured | 62.6% | Only GLM 5.2 measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | Gemini 3 Flash Preview | GLM 5.2 | Leader |
|---|---|---|---|
| AIME | 95.6% | Not measured | Only Gemini 3 Flash Preview measured |
| MGSM (Vals AI) | 93.3% | Not measured | Only Gemini 3 Flash Preview measured |
| AA Math Index | 97.0 | Not measured | Only Gemini 3 Flash Preview measured |
| AIME 2025 (Artificial Analysis run) | 97.0% | Not measured | Only Gemini 3 Flash Preview measured |
| OTIS Mock AIME | 95.6% | 86.4% | Gemini 3 Flash Preview |
| FrontierMath, tiers 1 to 3 | 51.2% | 59.2% | GLM 5.2 |
| FrontierMath, tier 4 | 17.1% | 29.3% | GLM 5.2 |
| ProofBench | 15.0% | 35.0% | GLM 5.2 |
| LMArena Text: math | Not measured | 1483 | Only GLM 5.2 measured |
| LMArena Text: mathematical work | Not measured | 1489 | Only GLM 5.2 measured |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Gemini 3 Flash Preview | GLM 5.2 | Leader |
|---|---|---|---|
| MMLU Pro | 88.6% | 86.7% | Gemini 3 Flash Preview |
| LegalBench (Vals AI) | 86.9% | 84.1% | Gemini 3 Flash Preview |
| CaseLaw (Vals AI) | 55.8% | Not measured | Only Gemini 3 Flash Preview measured |
| CorpFin (Vals AI) | 66.4% | 66.1% | Gemini 3 Flash Preview |
| TaxEval (Vals AI) | 73.9% | 73.3% | Gemini 3 Flash Preview |
| MortgageTax (Vals AI) | 68.7% | Not measured | Only Gemini 3 Flash Preview measured |
| MedQA (Vals AI) | 95.8% | Not measured | Only Gemini 3 Flash Preview measured |
| MedCode (Vals AI) | 55.9% | 40.8% | Gemini 3 Flash Preview |
| MMLU Pro (Artificial Analysis run) | 89.0% | Not measured | Only Gemini 3 Flash Preview measured |
| SimpleQA Verified | 66.8% | 34.2% | Gemini 3 Flash Preview |
| GeoBench | 88.0% | Not measured | Only Gemini 3 Flash Preview measured |
| LMArena Text: science | Not measured | 1489 | Only GLM 5.2 measured |
| LMArena Text: medicine and healthcare | Not measured | 1475 | Only GLM 5.2 measured |
| LMArena Text: legal and government | Not measured | 1486 | Only GLM 5.2 measured |
| LMArena Text: business and finance | Not measured | 1451 | Only GLM 5.2 measured |
| FACTS Benchmark Suite | 63.4% | Not measured | Only Gemini 3 Flash Preview measured |
| Neither model has a result on the other 2 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Gemini 3 Flash Preview | GLM 5.2 | Leader |
|---|---|---|---|
| Design Arena: websites | 1196 | 1285 | GLM 5.2 |
| Design Arena: UI components | Not measured | 1294 | Only GLM 5.2 measured |
| Design Arena: game dev | 1166 | 1268 | GLM 5.2 |
| Design Arena: data viz | Not measured | 1285 | Only GLM 5.2 measured |
| Design Arena: 3D | 1183 | 1287 | GLM 5.2 |
| Design Arena: all code categories | 1189 | 1287 | GLM 5.2 |
| Design Arena: SVG | Not measured | 1213 | Only GLM 5.2 measured |
| Design Arena: ASCII art | Not measured | 1191 | Only GLM 5.2 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index14
| Benchmark | Gemini 3 Flash Preview | GLM 5.2 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 51.8% | Not measured | Only Gemini 3 Flash Preview measured |
| MedScribe (Vals AI) | 69.9% | 83.5% | GLM 5.2 |
| Vals Multimodal Index | 52.2% | Not measured | Only Gemini 3 Flash Preview measured |
| IFBench | 78.0% | 73.3% | Gemini 3 Flash Preview |
| Long context reasoning (AA-LCR) | 78.0% | 78.3% | GLM 5.2 |
| DTBench | 89.1% | 93.6% | GLM 5.2 |
| LMCA | 43.1% | 45.8% | GLM 5.2 |
| Surface Evolver Bench | Not measured | 55.6% | Only GLM 5.2 measured |
| LMArena Text | Not measured | 1470 | Only GLM 5.2 measured |
| LMArena Text: instruction following | Not measured | 1466 | Only GLM 5.2 measured |
| LMArena Text: creative writing | Not measured | 1463 | Only GLM 5.2 measured |
| LMArena Text: English | Not measured | 1475 | Only GLM 5.2 measured |
| LMArena Text: non-English | Not measured | 1459 | Only GLM 5.2 measured |
| LMArena Text: Chinese | Not measured | 1522 | Only GLM 5.2 measured |
| LMArena Text: German | Not measured | 1470 | Only GLM 5.2 measured |
| LMArena Text: Japanese | Not measured | 1450 | Only GLM 5.2 measured |
| LMArena Text: Korean | Not measured | 1440 | Only GLM 5.2 measured |
| LMArena Text: French | Not measured | 1479 | Only GLM 5.2 measured |
| LMArena Text: Spanish | Not measured | 1478 | Only GLM 5.2 measured |
| LMArena Text: Russian | Not measured | 1468 | Only GLM 5.2 measured |
| LMArena Text: Polish | Not measured | 1456 | Only GLM 5.2 measured |
| LMArena Text: multi-turn | Not measured | 1469 | Only GLM 5.2 measured |
| LMArena Text: longer queries | Not measured | 1480 | Only GLM 5.2 measured |
| LMArena Text: writing and language | Not measured | 1463 | Only GLM 5.2 measured |
| LMArena Text: entertainment and media | Not measured | 1450 | Only GLM 5.2 measured |
| Neither model has a result on the other 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 3 Flash Preview | GLM 5.2 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Gemini 3 Flash Preview costs less
Repository review
50K input + 3K output tokens
Gemini 3 Flash Preview costs less
Agent loop
200K input + 10K output tokens
Gemini 3 Flash Preview costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Google Gemini 3 Flash Preview | Z.ai GLM 5.2 |
|---|---|---|
| Maker | Z.ai | |
| Weights | No public weights listed | Open weights |
| Released | December 17, 2025 | June 16, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.50 | $1.40 |
| Output $/Mtok | $3.00 | $4.40 |
| Coding index | 43.7 | 61.1 |
| Independent measurements behind it | 2 | 4 |
| Cost per solved task | $0.37 | $0.86 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 3 Flash Preview better than GLM 5.2 for coding?
Pick GLM 5.2 for coding: it scores 61.1 on the Vibe Coding Index against 43.7 for Gemini 3 Flash Preview. Pick Gemini 3 Flash Preview for output tokens 1.5x cheaper ($3.00 vs $4.40 per million) and a lower cost per solved task ($0.37 against $0.86).
Which is cheaper, Gemini 3 Flash Preview or GLM 5.2?
Gemini 3 Flash Preview costs $0.50 per million input tokens and $3.00 per million output tokens; GLM 5.2 costs $1.40 and $4.40. Per solved SWE-bench Verified task, Gemini 3 Flash Preview costs $0.37 and GLM 5.2 $0.86.
Which has the bigger context window, Gemini 3 Flash Preview or GLM 5.2?
Neither: both take 1.05M tokens.
How many benchmarks is the Gemini 3 Flash Preview vs GLM 5.2 comparison based on?
49 benchmarks have a result for both models as of October 22, 2026. Gemini 3 Flash Preview's coding index rests on 2 independent benchmarks and GLM 5.2's on 4. Where only one model has a result, the page says so instead of naming a winner.