Gemini 2.5 Pro Preview 06-05 vs GLM 4.7
Updated October 21, 2026. 7 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Gemini 2.5 Pro Preview 06-05 for coding: it scores 83.1 on the Vibe Coding Index against 33.6 for GLM 4.7.
Pick GLM 4.7 when output tokens cost 5.1x less, or when what matters is LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.
- Shared results
- 7
- Gemini 2.5 Pro Preview 06-05 only
- 7
- GLM 4.7 only
- 73
- Like-for-like categories
- 3 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
Gemini 2.5 Pro Preview 06-05
Gemini 2.5 Pro Preview 06-05 scores 83.1 against 33.6.
One benchmark behind each score
Intelligence
AA Intelligence Index
No call
Only GLM 4.7 has a AA Intelligence Index result, 22.2.
Directional only
Reasoning
GPQA Diamond
No call
Only GLM 4.7 has a GPQA Diamond result, 80.0%.
Directional only
Math
AIME
No call
Only GLM 4.7 has a AIME result, 93.3%.
Directional only
Knowledge
MMLU Pro
No call
Only GLM 4.7 has a MMLU Pro result, 82.7%.
Directional only
Web design
Design Arena: websites
No call
Only GLM 4.7 has a Design Arena: websites result, 1226.
Directional only
Long documents
Listed context window
Gemini 2.5 Pro Preview 06-05
Gemini 2.5 Pro Preview 06-05 takes 1.05M tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GLM 4.7
Gemini 2.5 Pro Preview 06-05 $0.0063, GLM 4.7 $0.0015 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GLM 4.7 has the number, $0.29.
Directional only
At a glance
- Coding index
- Gemini 2.5 Pro Preview 06-05 83.1 from 1 benchmark, GLM 4.7 33.6 from 1 benchmark.
- Widest category
- Coding, 7.3 points apart on average over 2 shared benchmarks.
- Widest single gap
- SimpleBench: Gemini 2.5 Pro Preview 06-05 62.4% against GLM 4.7 47.7%, 14.7 points apart on a 0 to 100 scale.
- Output price
- Gemini 2.5 Pro Preview 06-05 $10.00 against GLM 4.7 $1.98 per million output tokens, 5.1x apart.
- Context window
- Gemini 2.5 Pro Preview 06-05 takes 1.05M tokens, GLM 4.7 205K.
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 2.5 Pro Preview 06-05 | Bars | GLM 4.7 | Ties |
|---|---|---|---|---|
| Coding | 0 | 2 | ||
| Reasoning | 2 | 2 | ||
| Knowledge | 1 | 0 | ||
| All shared boards | 3 | 4 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index02
| Benchmark | Gemini 2.5 Pro Preview 06-05 | GLM 4.7 | Leader |
|---|---|---|---|
| Aider polyglot | 83.1% | Not measured | Only Gemini 2.5 Pro Preview 06-05 measured |
| LMArena WebDev | Not measured | 1435 | Only GLM 4.7 measured |
| AA Coding Index | Not measured | 45.3 | Only GLM 4.7 measured |
| LiveCodeBench (Vals AI) | 79.2% | 82.2% | GLM 4.7 |
| SWE-bench Verified (Vals AI) | Not measured | 69.4% | Only GLM 4.7 measured |
| LiveCodeBench (Artificial Analysis run) | 77.8% | 89.4% | GLM 4.7 |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 31.8% | Only GLM 4.7 measured |
| Terminal-Bench | Not measured | 33.4% | Only GLM 4.7 measured |
| GSO-Bench | 3.9% | Not measured | Only Gemini 2.5 Pro Preview 06-05 measured |
| ALE-Bench | Not measured | 399.5 | Only GLM 4.7 measured |
| LMArena Text: coding | Not measured | 1454 | Only GLM 4.7 measured |
| LMArena Text: software and IT | Not measured | 1453 | Only GLM 4.7 measured |
| LMArena WebDev: React | Not measured | 1420 | Only GLM 4.7 measured |
| LMArena WebDev: HTML | Not measured | 1447 | Only GLM 4.7 measured |
| Neither model has a result on the other 24 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Gemini 2.5 Pro Preview 06-05 | GLM 4.7 | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 22.2 | Only GLM 4.7 measured |
| Epoch Capabilities Index | Not measured | 143.6 | Only GLM 4.7 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Gemini 2.5 Pro Preview 06-05 | GLM 4.7 | Leader |
|---|---|---|---|
| Design Arena: agents building full-stack apps | Not measured | 1050 | Only GLM 4.7 measured |
| Design Arena: agents building mobile apps | Not measured | 1105 | Only GLM 4.7 measured |
| Design Arena: agents building Android apps | Not measured | 1118 | Only GLM 4.7 measured |
| Design Arena: agents building Godot games | Not measured | 1058 | Only GLM 4.7 measured |
| τ²-Bench Telecom | Not measured | 95.9% | Only GLM 4.7 measured |
| METR time horizons | 55.4% | Not measured | Only Gemini 2.5 Pro Preview 06-05 measured |
| Remote Labor Index | 0.8% | Not measured | Only Gemini 2.5 Pro Preview 06-05 measured |
| DeepResearch Bench | 42.8% | Not measured | Only Gemini 2.5 Pro Preview 06-05 measured |
| Vending-Bench 2 | Not measured | $2,377 | Only GLM 4.7 measured |
| Neither model has a result on the other 30 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | Gemini 2.5 Pro Preview 06-05 | GLM 4.7 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 80.0% | Only GLM 4.7 measured |
| GPQA Diamond (Artificial Analysis run) | 83.6% | 85.9% | GLM 4.7 |
| Humanity's Last Exam (Artificial Analysis run) | 19.9% | 27.4% | GLM 4.7 |
| GPQA Diamond (Epoch AI run) | 84.8% | 83.3% | Gemini 2.5 Pro Preview 06-05 |
| SimpleBench | 62.4% | 47.7% | Gemini 2.5 Pro Preview 06-05 |
| Chess puzzles | Not measured | 21.0% | Only GLM 4.7 measured |
| VPCT | 46.4% | Not measured | Only Gemini 2.5 Pro Preview 06-05 measured |
| LMArena Text: hard prompts | Not measured | 1443 | Only GLM 4.7 measured |
| LMArena Text: expert | Not measured | 1424 | Only GLM 4.7 measured |
| LMArena Text: hard prompts in English | Not measured | 1452 | Only GLM 4.7 measured |
| Neither model has a result on the other 11 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Gemini 2.5 Pro Preview 06-05 | GLM 4.7 | Leader |
|---|---|---|---|
| AIME | Not measured | 93.3% | Only GLM 4.7 measured |
| MGSM (Vals AI) | Not measured | 88.2% | Only GLM 4.7 measured |
| AA Math Index | Not measured | 95.0 | Only GLM 4.7 measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 95.0% | Only GLM 4.7 measured |
| OTIS Mock AIME | Not measured | 83.3% | Only GLM 4.7 measured |
| ProofBench | Not measured | 6.0% | Only GLM 4.7 measured |
| LMArena Text: math | Not measured | 1424 | Only GLM 4.7 measured |
| LMArena Text: mathematical work | Not measured | 1411 | Only GLM 4.7 measured |
| Neither model has a result on the other 5 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemini 2.5 Pro Preview 06-05 | GLM 4.7 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 82.7% | Only GLM 4.7 measured |
| LegalBench (Vals AI) | Not measured | 83.4% | Only GLM 4.7 measured |
| CaseLaw (Vals AI) | Not measured | 54.9% | Only GLM 4.7 measured |
| CorpFin (Vals AI) | Not measured | 46.4% | Only GLM 4.7 measured |
| TaxEval (Vals AI) | Not measured | 68.8% | Only GLM 4.7 measured |
| MedQA (Vals AI) | Not measured | 93.7% | Only GLM 4.7 measured |
| MedCode (Vals AI) | Not measured | 32.8% | Only GLM 4.7 measured |
| MMLU Pro (Artificial Analysis run) | 85.8% | 85.6% | Gemini 2.5 Pro Preview 06-05 |
| SimpleQA Verified | Not measured | 32.2% | Only GLM 4.7 measured |
| LMArena Text: science | Not measured | 1457 | Only GLM 4.7 measured |
| LMArena Text: medicine and healthcare | Not measured | 1469 | Only GLM 4.7 measured |
| LMArena Text: legal and government | Not measured | 1444 | Only GLM 4.7 measured |
| LMArena Text: business and finance | Not measured | 1429 | Only GLM 4.7 measured |
| Neither model has a result on the other 4 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Gemini 2.5 Pro Preview 06-05 | GLM 4.7 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1226 | Only GLM 4.7 measured |
| Design Arena: UI components | Not measured | 1199 | Only GLM 4.7 measured |
| Design Arena: game dev | Not measured | 1189 | Only GLM 4.7 measured |
| Design Arena: data viz | Not measured | 1195 | Only GLM 4.7 measured |
| Design Arena: 3D | Not measured | 1191 | Only GLM 4.7 measured |
| Design Arena: all code categories | Not measured | 1217 | Only GLM 4.7 measured |
| Design Arena: SVG | Not measured | 1142 | Only GLM 4.7 measured |
| Design Arena: ASCII art | Not measured | 1165 | Only GLM 4.7 measured |
| Neither model has a result on the other 1 board here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index23 boards, none shared
| Benchmark | Gemini 2.5 Pro Preview 06-05 | GLM 4.7 | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | Not measured | 68.6% | Only GLM 4.7 measured |
| IFBench | Not measured | 67.9% | Only GLM 4.7 measured |
| Long context reasoning (AA-LCR) | Not measured | 71.0% | Only GLM 4.7 measured |
| Fiction.LiveBench | 91.7% | Not measured | Only Gemini 2.5 Pro Preview 06-05 measured |
| CL-bench | Not measured | 15.9% | Only GLM 4.7 measured |
| CL-bench Life | Not measured | 10.9% | Only GLM 4.7 measured |
| LMArena Text | Not measured | 1435 | Only GLM 4.7 measured |
| LMArena Text: instruction following | Not measured | 1412 | Only GLM 4.7 measured |
| LMArena Text: creative writing | Not measured | 1401 | Only GLM 4.7 measured |
| LMArena Text: English | Not measured | 1453 | Only GLM 4.7 measured |
| LMArena Text: non-English | Not measured | 1417 | Only GLM 4.7 measured |
| LMArena Text: Chinese | Not measured | 1495 | Only GLM 4.7 measured |
| LMArena Text: German | Not measured | 1426 | Only GLM 4.7 measured |
| LMArena Text: Japanese | Not measured | 1439 | Only GLM 4.7 measured |
| LMArena Text: Korean | Not measured | 1399 | Only GLM 4.7 measured |
| LMArena Text: French | Not measured | 1432 | Only GLM 4.7 measured |
| LMArena Text: Spanish | Not measured | 1434 | Only GLM 4.7 measured |
| LMArena Text: Russian | Not measured | 1423 | Only GLM 4.7 measured |
| LMArena Text: Polish | Not measured | 1435 | Only GLM 4.7 measured |
| LMArena Text: multi-turn | Not measured | 1446 | Only GLM 4.7 measured |
| LMArena Text: longer queries | Not measured | 1432 | Only GLM 4.7 measured |
| LMArena Text: writing and language | Not measured | 1411 | Only GLM 4.7 measured |
| LMArena Text: entertainment and media | Not measured | 1400 | Only GLM 4.7 measured |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 2.5 Pro Preview 06-05 | GLM 4.7 | 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 4.7 costs less
Repository review
50K input + 3K output tokens
GLM 4.7 costs less
Agent loop
200K input + 10K output tokens
GLM 4.7 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 2.5 Pro Preview 06-05 | Z.ai GLM 4.7 |
|---|---|---|
| Maker | Z.ai | |
| Weights | No public weights listed | Open weights |
| Released | June 5, 2025 | December 22, 2025 |
| Context window | 1.05M | 205K |
| Input $/Mtok | $1.25 | $0.54 |
| Output $/Mtok | $10.00 | $1.98 |
| Coding index | 83.1 | 33.6 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | $0.29 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 2.5 Pro Preview 06-05 better than GLM 4.7 for coding?
Pick Gemini 2.5 Pro Preview 06-05 for coding: it scores 83.1 on the Vibe Coding Index against 33.6 for GLM 4.7. Pick GLM 4.7 when output tokens cost 5.1x less, or when what matters is LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.
Which is cheaper, Gemini 2.5 Pro Preview 06-05 or GLM 4.7?
Gemini 2.5 Pro Preview 06-05 costs $1.25 per million input tokens and $10.00 per million output tokens; GLM 4.7 costs $0.54 and $1.98. Cost per solved task is known for GLM 4.7 only.
Which has the bigger context window, Gemini 2.5 Pro Preview 06-05 or GLM 4.7?
Gemini 2.5 Pro Preview 06-05, with 1.05M tokens against 205K.
How many benchmarks is the Gemini 2.5 Pro Preview 06-05 vs GLM 4.7 comparison based on?
7 benchmarks have a result for both models as of October 21, 2026. Gemini 2.5 Pro Preview 06-05's coding index rests on 1 independent benchmark and GLM 4.7's on 1. Where only one model has a result, the page says so instead of naming a winner.