Gemini 3.1 Pro Preview vs GLM 5.2
Updated October 21, 2026. 93 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick GLM 5.2 for coding: it scores 57.7 on the Vibe Coding Index against 35.3 for Gemini 3.1 Pro Preview.
Pick Gemini 3.1 Pro Preview when what matters is LiveCodeBench (Vals AI) or Terminal-Bench 2.1 (Vals AI), where it leads.
- Shared results
- 93
- Gemini 3.1 Pro Preview only
- 38
- GLM 5.2 only
- 4
- Like-for-like categories
- 8 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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, four public coding benchmarks
GLM 5.2
GLM 5.2 scores 57.7 against 35.3.
One benchmark behind each score
Intelligence
AA Intelligence Index
GLM 5.2
GLM 5.2 leads, 33.7 against 29.7.
Same board, both measured
Agentic work
AA Agentic Index
GLM 5.2
GLM 5.2 leads, 38.4 against 8.2.
Same board, both measured
Reasoning
GPQA Diamond
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 95.5% against 85.6%.
Same board, both measured
Math
AIME
No call
Only Gemini 3.1 Pro Preview has a AIME result, 98.1%.
Directional only
Knowledge
MMLU Pro
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 91.0% against 86.7%.
Same board, both measured
Web design
Design Arena: websites
GLM 5.2
GLM 5.2 leads, 1285 against 1234.
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
GLM 5.2
Gemini 3.1 Pro Preview $0.0080, GLM 5.2 $0.0035 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GLM 5.2
Gemini 3.1 Pro Preview $0.99, GLM 5.2 $0.86.
Published attempt cost and pass rate
At a glance
- Coding index
- Gemini 3.1 Pro Preview 35.3 from 1 benchmark, GLM 5.2 57.7 from 1 benchmark.
- Widest category
- Agentic work, 13.3 points apart on average over 17 shared benchmarks.
- Widest single gap
- ARC-AGI-2: Gemini 3.1 Pro Preview 77.1% against GLM 5.2 22.8%, 54.3 points apart on a 0 to 100 scale.
- Output price
- Gemini 3.1 Pro Preview $12.00 against GLM 5.2 $7.00 per million output tokens, 1.7x 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 3.1 Pro Preview | Bars | GLM 5.2 | Ties |
|---|---|---|---|---|
| Coding | 7 | 8 | 1 tie | |
| Intelligence | 0 | 1 | ||
| Agentic work | 1 | 15 | 1 tie | |
| Reasoning | 11 | 2 | ||
| Math | 3 | 3 | ||
| Knowledge | 8 | 2 | ||
| Web design | 2 | 6 | ||
| General | 20 | 2 | ||
| All shared boards | 52 | 39 | 2 ties |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index78
| Benchmark | Gemini 3.1 Pro Preview | GLM 5.2 | Leader |
|---|---|---|---|
| LMArena WebDev | 1447 | 1604 | GLM 5.2 |
| AA Coding Index | 68.8 | 68.8 | Tie |
| LiveCodeBench (Vals AI) | 88.5% | 69.5% | Gemini 3.1 Pro Preview |
| SWE-bench Verified (Vals AI) | 78.8% | 82.8% | GLM 5.2 |
| Terminal-Bench 4 (Vals AI) | 2.5% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Vibe Code Bench (Vals AI) | 32.0% | 64.0% | GLM 5.2 |
| Code migration (Vals AI) | 17.3% | 37.9% | GLM 5.2 |
| ProgramBench (Vals AI) | 0.0% | 0.5% | GLM 5.2 |
| IOI (Vals AI) | 51.8% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench 2.1 (Vals AI) | 70.8% | 67.8% | Gemini 3.1 Pro Preview |
| Vibe Code Bench 1-100 (Vals AI) | 6.7% | Not measured | Only Gemini 3.1 Pro Preview measured |
| SkillsBench (Vals AI) | Not measured | 45.1% | Only GLM 5.2 measured |
| SciCode | 58.7% | 51.2% | Gemini 3.1 Pro Preview |
| Terminal-Bench Hard (Artificial Analysis run) | 53.8% | 50.8% | Gemini 3.1 Pro Preview |
| Terminal-Bench | 80.2% | Not measured | Only Gemini 3.1 Pro Preview measured |
| FrontierCode | Not measured | 24.5% | Only GLM 5.2 measured |
| GSO-Bench | 22.6% | Not measured | Only Gemini 3.1 Pro Preview measured |
| WeirdML | 72.1% | 70.1% | Gemini 3.1 Pro Preview |
| MirrorCode | 8.9% | Not measured | Only Gemini 3.1 Pro Preview measured |
| ALE-Bench | 1160.6 | 1047.0 | Gemini 3.1 Pro Preview |
| LMArena Text: coding | 1484 | 1487 | GLM 5.2 |
| LMArena Text: software and IT | 1487 | 1486 | Gemini 3.1 Pro Preview |
| LMArena WebDev: React | 1438 | 1617 | GLM 5.2 |
| LMArena WebDev: HTML | 1490 | 1565 | GLM 5.2 |
| LMArena WebDev: from an image | 1481 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 13 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemini 3.1 Pro Preview | GLM 5.2 | Leader |
|---|---|---|---|
| AA Intelligence Index | 29.7 | 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 index115
| Benchmark | Gemini 3.1 Pro Preview | GLM 5.2 | Leader |
|---|---|---|---|
| AA Agentic Index | 8.2 | 38.4 | GLM 5.2 |
| Design Arena: agents building web apps | 1125 | 1222 | GLM 5.2 |
| Design Arena: agents building full-stack apps | 1068 | 1241 | GLM 5.2 |
| Design Arena: agents building mobile apps | 1094 | 1160 | GLM 5.2 |
| Design Arena: agents building Android apps | 1055 | 1184 | GLM 5.2 |
| Design Arena: agents building Godot games | 1236 | 1142 | Gemini 3.1 Pro Preview |
| Design Arena: agents building games | 1114 | 1206 | GLM 5.2 |
| Design Arena: HTML slides | 1153 | 1175 | GLM 5.2 |
| Design Arena: PowerPoint slides | 1064 | 1195 | GLM 5.2 |
| SREBench (Vals AI) | 0.0% | 0.0% | Tie |
| Finance Agent (Vals AI) | 43.0% | 49.7% | GLM 5.2 |
| Tax Agent Bench (Vals AI) | 9.3% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Legal Research Bench (Vals AI) | 20.7% | 31.3% | GLM 5.2 |
| Excel Modeling Benchmark (Vals AI) | 52.6% | 61.5% | GLM 5.2 |
| BioMysteryBench (Vals AI) | 60.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench-Science (Vals AI) | 1.4% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Vals Science Index | 27.4% | Not measured | Only Gemini 3.1 Pro Preview measured |
| τ²-Bench Telecom | 95.6% | 99.1% | GLM 5.2 |
| APEX-Agents | 35.1% | 45.2% | GLM 5.2 |
| METR time horizons | 77.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| BALROG | 57.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| DeepResearch Bench | 47.8% | Not measured | Only Gemini 3.1 Pro Preview measured |
| PostTrainBench | 22.0% | 31.7% | GLM 5.2 |
| Vending-Bench 2 | $911 | $8,314 | GLM 5.2 |
| Neither model has a result on the other 15 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index112
| Benchmark | Gemini 3.1 Pro Preview | GLM 5.2 | Leader |
|---|---|---|---|
| GPQA Diamond | 95.5% | 85.6% | Gemini 3.1 Pro Preview |
| MysteryMechanism (Vals AI) | 20.7% | Not measured | Only Gemini 3.1 Pro Preview measured |
| MMMU Pro (Vals AI) | 88.2% | Not measured | Only Gemini 3.1 Pro Preview measured |
| GPQA Diamond (Artificial Analysis run) | 94.1% | 89.5% | Gemini 3.1 Pro Preview |
| Humanity's Last Exam (Artificial Analysis run) | 47.0% | 41.1% | Gemini 3.1 Pro Preview |
| GPQA Diamond (Epoch AI run) | 94.4% | 91.9% | Gemini 3.1 Pro Preview |
| ARC-AGI | 98.0% | 77.0% | Gemini 3.1 Pro Preview |
| ARC-AGI-2 | 77.1% | 22.8% | Gemini 3.1 Pro Preview |
| SimpleBench | 79.6% | 58.8% | Gemini 3.1 Pro Preview |
| Chess puzzles | 51.0% | 22.0% | Gemini 3.1 Pro Preview |
| Mystery game puzzles | 34.0% | 19.0% | Gemini 3.1 Pro Preview |
| EBR-bench | 14.3% | 9.5% | Gemini 3.1 Pro Preview |
| LMArena Text: hard prompts | 1485 | 1481 | Gemini 3.1 Pro Preview |
| LMArena Text: expert | 1483 | 1487 | GLM 5.2 |
| LMArena Text: hard prompts in English | 1480 | 1481 | GLM 5.2 |
| LMArena Vision: diagrams | 1311 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: homework | 1316 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index33
| Benchmark | Gemini 3.1 Pro Preview | GLM 5.2 | Leader |
|---|---|---|---|
| AIME | 98.1% | Not measured | Only Gemini 3.1 Pro Preview measured |
| OTIS Mock AIME | 95.6% | 86.4% | Gemini 3.1 Pro Preview |
| FrontierMath, tiers 1 to 3 | 59.6% | 59.2% | Gemini 3.1 Pro Preview |
| FrontierMath, tier 4 | 26.8% | 29.3% | GLM 5.2 |
| ProofBench | 26.0% | 35.0% | GLM 5.2 |
| LMArena Text: math | 1486 | 1483 | Gemini 3.1 Pro Preview |
| LMArena Text: mathematical work | 1478 | 1489 | GLM 5.2 |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index82
| Benchmark | Gemini 3.1 Pro Preview | GLM 5.2 | Leader |
|---|---|---|---|
| MMLU Pro | 91.0% | 86.7% | Gemini 3.1 Pro Preview |
| LegalBench (Vals AI) | 87.4% | 84.1% | Gemini 3.1 Pro Preview |
| CaseLaw (Vals AI) | 64.8% | Not measured | Only Gemini 3.1 Pro Preview measured |
| CorpFin (Vals AI) | 64.5% | 66.1% | GLM 5.2 |
| TaxEval (Vals AI) | 72.9% | 73.3% | GLM 5.2 |
| MortgageTax (Vals AI) | 69.4% | Not measured | Only Gemini 3.1 Pro Preview measured |
| MedQA (Vals AI) | 96.4% | Not measured | Only Gemini 3.1 Pro Preview measured |
| MedCode (Vals AI) | 59.1% | 40.8% | Gemini 3.1 Pro Preview |
| SimpleQA Verified | 73.5% | 34.2% | Gemini 3.1 Pro Preview |
| LMArena Text: science | 1497 | 1489 | Gemini 3.1 Pro Preview |
| LMArena Text: medicine and healthcare | 1486 | 1475 | Gemini 3.1 Pro Preview |
| LMArena Text: legal and government | 1487 | 1486 | Gemini 3.1 Pro Preview |
| LMArena Text: business and finance | 1459 | 1451 | Gemini 3.1 Pro Preview |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index26
| Benchmark | Gemini 3.1 Pro Preview | GLM 5.2 | Leader |
|---|---|---|---|
| Design Arena: websites | 1234 | 1285 | GLM 5.2 |
| Design Arena: UI components | 1226 | 1296 | GLM 5.2 |
| Design Arena: game dev | 1203 | 1268 | GLM 5.2 |
| Design Arena: data viz | 1209 | 1285 | GLM 5.2 |
| Design Arena: 3D | 1234 | 1288 | GLM 5.2 |
| Design Arena: all code categories | 1231 | 1288 | GLM 5.2 |
| Design Arena: SVG | 1285 | 1214 | Gemini 3.1 Pro Preview |
| Design Arena: ASCII art | 1270 | 1190 | Gemini 3.1 Pro Preview |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index202
| Benchmark | Gemini 3.1 Pro Preview | GLM 5.2 | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | 53.8% | Not measured | Only Gemini 3.1 Pro Preview measured |
| SAGE (Vals AI) | 48.7% | Not measured | Only Gemini 3.1 Pro Preview measured |
| MedScribe (Vals AI) | 76.1% | 83.5% | GLM 5.2 |
| Vals Multimodal Index | 56.1% | Not measured | Only Gemini 3.1 Pro Preview measured |
| IFBench | 77.1% | 73.3% | Gemini 3.1 Pro Preview |
| Long context reasoning (AA-LCR) | 82.0% | 78.3% | Gemini 3.1 Pro Preview |
| DTBench | 97.1% | 93.6% | Gemini 3.1 Pro Preview |
| LMCA | 53.8% | 45.8% | Gemini 3.1 Pro Preview |
| CL-bench | 20.8% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Surface Evolver Bench | Not measured | 55.6% | Only GLM 5.2 measured |
| Furniture assembly | 26.7% | Not measured | Only Gemini 3.1 Pro Preview measured |
| ExploitBench | 26.1% | Not measured | Only Gemini 3.1 Pro Preview measured |
| CL-bench Life | 16.9% | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text | 1480 | 1470 | Gemini 3.1 Pro Preview |
| LMArena Text: instruction following | 1466 | 1466 | GLM 5.2 |
| LMArena Text: creative writing | 1482 | 1463 | Gemini 3.1 Pro Preview |
| LMArena Vision | 1296 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: English | 1478 | 1475 | Gemini 3.1 Pro Preview |
| LMArena Text: non-English | 1476 | 1459 | Gemini 3.1 Pro Preview |
| LMArena Text: Chinese | 1527 | 1522 | Gemini 3.1 Pro Preview |
| LMArena Text: German | 1490 | 1470 | Gemini 3.1 Pro Preview |
| LMArena Text: Japanese | 1491 | 1450 | Gemini 3.1 Pro Preview |
| LMArena Text: Korean | 1455 | 1440 | Gemini 3.1 Pro Preview |
| LMArena Text: French | 1487 | 1479 | Gemini 3.1 Pro Preview |
| LMArena Text: Spanish | 1481 | 1478 | Gemini 3.1 Pro Preview |
| LMArena Text: Russian | 1497 | 1468 | Gemini 3.1 Pro Preview |
| LMArena Text: Polish | 1498 | 1456 | Gemini 3.1 Pro Preview |
| LMArena Text: multi-turn | 1487 | 1469 | Gemini 3.1 Pro Preview |
| LMArena Text: longer queries | 1482 | 1480 | Gemini 3.1 Pro Preview |
| LMArena Text: writing and language | 1481 | 1463 | Gemini 3.1 Pro Preview |
| LMArena Text: entertainment and media | 1465 | 1450 | Gemini 3.1 Pro Preview |
| LMArena Vision: English | 1287 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: Chinese | 1364 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: reading text | 1304 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: humor | 1322 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: captioning | 1345 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: recognizing things | 1330 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: creative writing | 1324 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Document | 1444 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 7 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 3.1 Pro 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
GLM 5.2 costs less
Repository review
50K input + 3K output tokens
GLM 5.2 costs less
Agent loop
200K input + 10K output tokens
GLM 5.2 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 3.1 Pro Preview | Z.ai GLM 5.2 |
|---|---|---|
| Maker | Z.ai | |
| Weights | No public weights listed | Open weights |
| Released | February 19, 2026 | June 16, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $2.00 | $0.0341 |
| Output $/Mtok | $12.00 | $7.00 |
| Coding index | 35.3 | 57.7 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | $0.99 | $0.86 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 3.1 Pro Preview better than GLM 5.2 for coding?
Pick GLM 5.2 for coding: it scores 57.7 on the Vibe Coding Index against 35.3 for Gemini 3.1 Pro Preview. Pick Gemini 3.1 Pro Preview when what matters is LiveCodeBench (Vals AI) or Terminal-Bench 2.1 (Vals AI), where it leads.
Which is cheaper, Gemini 3.1 Pro Preview or GLM 5.2?
Gemini 3.1 Pro Preview costs $2.00 per million input tokens and $12.00 per million output tokens; GLM 5.2 costs $0.0341 and $7.00. Per solved SWE-bench Verified task, Gemini 3.1 Pro Preview costs $0.99 and GLM 5.2 $0.86.
Which has the bigger context window, Gemini 3.1 Pro Preview or GLM 5.2?
Neither: both take 1.05M tokens.
How many benchmarks is the Gemini 3.1 Pro Preview vs GLM 5.2 comparison based on?
93 benchmarks have a result for both models as of October 21, 2026. Gemini 3.1 Pro Preview's coding index rests on 1 independent benchmark and GLM 5.2's on 1. Where only one model has a result, the page says so instead of naming a winner.