DeepSeek V4 Flash Vision Exp vs GLM 4.7
DeepSeek V4 Flash Vision Exp leads GLM 4.7 on the Artificial Analysis Intelligence Index, 34.8 to 22.2, and DeepSeek V4 Flash Vision Exp costs 1.7x less per output token ($1.32 vs $2.20 per million). Updated October 22, 2026; 5 benchmarks have a result for both.
DeepSeek V4 Flash Vision Exp or GLM 4.7: which to pick
Only GLM 4.7 has a coding score, 55.1 on the Vibe Coding Index; DeepSeek V4 Flash Vision Exp has none, so the two cannot be ranked on coding.
Pick DeepSeek V4 Flash Vision Exp for output tokens 1.7x cheaper ($1.32 vs $2.20 per million) and a larger context window (1.05M against 205K tokens).
- Shared results
- 5
- DeepSeek V4 Flash Vision Exp only
- 9
- GLM 4.7 only
- 76
- Like-for-like categories
- 4 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
No call
Only GLM 4.7 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
DeepSeek V4 Flash Vision Exp
DeepSeek V4 Flash Vision Exp leads, 34.8 against 22.2.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V4 Flash Vision Exp has a AA Agentic Index result, 47.5.
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, 1225.
Directional only
Long documents
Listed context window
DeepSeek V4 Flash Vision Exp
DeepSeek V4 Flash Vision Exp takes 1.05M tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Flash Vision Exp
DeepSeek V4 Flash Vision Exp $0.0011, GLM 4.7 $0.0017 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
- DeepSeek V4 Flash Vision Exp not benchmarked, GLM 4.7 55.1 from 2 benchmarks.
- Widest category
- Coding, 19.7 points apart on average over 1 shared benchmark.
- Widest single gap
- AA Coding Index: DeepSeek V4 Flash Vision Exp 65.0 against GLM 4.7 45.3, 19.7 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Flash Vision Exp $1.32 against GLM 4.7 $2.20 per million output tokens, 1.7x apart.
- Context window
- DeepSeek V4 Flash Vision Exp 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 | DeepSeek V4 Flash Vision Exp | Bars | GLM 4.7 | Ties |
|---|---|---|---|---|
| Coding | 1 | 0 | ||
| Intelligence | 1 | 0 | ||
| Reasoning | 2 | 0 | ||
| General | 1 | 0 | ||
| All shared boards | 5 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index10
| Benchmark | DeepSeek V4 Flash Vision Exp | GLM 4.7 | Leader |
|---|---|---|---|
| LiveBench coding | 37.6% | Not measured | Only DeepSeek V4 Flash Vision Exp measured |
| LMArena WebDev | Not measured | 1435 | Only GLM 4.7 measured |
| AA Coding Index | 65.0 | 45.3 | DeepSeek V4 Flash Vision Exp |
| LiveCodeBench (Vals AI) | Not measured | 82.2% | Only GLM 4.7 measured |
| SWE-bench Verified (Vals AI) | Not measured | 69.4% | Only GLM 4.7 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 89.4% | Only GLM 4.7 measured |
| SciCode | 49.7% | Not measured | Only DeepSeek V4 Flash Vision Exp measured |
| 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 |
| 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 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V4 Flash Vision Exp | GLM 4.7 | Leader |
|---|---|---|---|
| AA Intelligence Index | 34.8 | 22.2 | DeepSeek V4 Flash Vision Exp |
| Epoch Capabilities Index | Not measured | 143.6 | Only GLM 4.7 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | DeepSeek V4 Flash Vision Exp | GLM 4.7 | Leader |
|---|---|---|---|
| AA Agentic Index | 47.5 | Not measured | Only DeepSeek V4 Flash Vision Exp measured |
| 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 | 1112 | Only GLM 4.7 measured |
| Design Arena: agents building Godot games | Not measured | 1058 | Only GLM 4.7 measured |
| LiveBench research | 69.2% | Not measured | Only DeepSeek V4 Flash Vision Exp measured |
| LiveBench browser | 64.0% | Not measured | Only DeepSeek V4 Flash Vision Exp measured |
| LiveBench long agentic | 39.0% | Not measured | Only DeepSeek V4 Flash Vision Exp measured |
| τ²-Bench Telecom | Not measured | 95.9% | Only GLM 4.7 measured |
| Vending-Bench 2 | Not measured | $2,377 | Only GLM 4.7 measured |
| BrowseComp-Plus | Not measured | 64.7% | 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 index20
| Benchmark | DeepSeek V4 Flash Vision Exp | GLM 4.7 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 80.0% | Only GLM 4.7 measured |
| LiveBench reasoning | 85.4% | Not measured | Only DeepSeek V4 Flash Vision Exp measured |
| GPQA Diamond (Artificial Analysis run) | 91.3% | 85.9% | DeepSeek V4 Flash Vision Exp |
| Humanity's Last Exam (Artificial Analysis run) | 34.5% | 27.4% | DeepSeek V4 Flash Vision Exp |
| GPQA Diamond (Epoch AI run) | Not measured | 83.3% | Only GLM 4.7 measured |
| SimpleBench | Not measured | 47.7% | Only GLM 4.7 measured |
| Chess puzzles | Not measured | 21.0% | Only GLM 4.7 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 12 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | DeepSeek V4 Flash Vision Exp | 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 | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index13 boards, none shared
| Benchmark | DeepSeek V4 Flash Vision Exp | 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) | Not measured | 85.6% | Only GLM 4.7 measured |
| 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 5 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | DeepSeek V4 Flash Vision Exp | GLM 4.7 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1225 | Only GLM 4.7 measured |
| Design Arena: UI components | Not measured | 1196 | Only GLM 4.7 measured |
| Design Arena: game dev | Not measured | 1188 | Only GLM 4.7 measured |
| Design Arena: data viz | Not measured | 1195 | Only GLM 4.7 measured |
| Design Arena: 3D | Not measured | 1190 | Only GLM 4.7 measured |
| Design Arena: all code categories | Not measured | 1216 | 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 |
| LiveBench design | 70.7% | Not measured | Only DeepSeek V4 Flash Vision Exp measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V4 Flash Vision Exp | GLM 4.7 | Leader |
|---|---|---|---|
| LiveBench data analysis | 79.5% | Not measured | Only DeepSeek V4 Flash Vision Exp measured |
| 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) | 81.3% | 71.0% | DeepSeek V4 Flash Vision Exp |
| 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 | DeepSeek V4 Flash Vision Exp | 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
DeepSeek V4 Flash Vision Exp costs less
Repository review
50K input + 3K output tokens
DeepSeek V4 Flash Vision Exp costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4 Flash Vision Exp 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 | DeepSeek V4 Flash Vision Exp | Z.ai GLM 4.7 |
|---|---|---|
| Maker | DeepSeek | Z.ai |
| Weights | Open weights | Open weights |
| Released | August 21, 2026 | December 22, 2025 |
| Context window | 1.05M | 205K |
| Input $/Mtok | $0.44 | $0.60 |
| Output $/Mtok | $1.32 | $2.20 |
| Coding index | Not benchmarked | 55.1 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | Not computable | $0.29 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Flash Vision Exp better than GLM 4.7 for coding?
Only GLM 4.7 has a coding score, 55.1 on the Vibe Coding Index; DeepSeek V4 Flash Vision Exp has none, so the two cannot be ranked on coding. Pick DeepSeek V4 Flash Vision Exp for output tokens 1.7x cheaper ($1.32 vs $2.20 per million) and a larger context window (1.05M against 205K tokens).
Which is cheaper, DeepSeek V4 Flash Vision Exp or GLM 4.7?
DeepSeek V4 Flash Vision Exp costs $0.44 per million input tokens and $1.32 per million output tokens; GLM 4.7 costs $0.60 and $2.20. Cost per solved task is known for GLM 4.7 only.
Which has the bigger context window, DeepSeek V4 Flash Vision Exp or GLM 4.7?
DeepSeek V4 Flash Vision Exp, with 1.05M tokens against 205K.
How many benchmarks is the DeepSeek V4 Flash Vision Exp vs GLM 4.7 comparison based on?
5 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4 Flash Vision Exp's coding index rests on 1 independent benchmark and GLM 4.7's on 2. Where only one model has a result, the page says so instead of naming a winner.