Qwen3.7 Max vs Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B leads Qwen3.7 Max on the Artificial Analysis Intelligence Index, 39.9 to 29.5, and Qwen3.7 Max costs 1.4x less per output token ($4.425 vs $6.00 per million). Updated October 22, 2026; 7 benchmarks have a result for both.
Qwen3.7 Max or Qwen3.8 2.4T A95B: which to pick
Only Qwen3.7 Max has a coding score, 54.1 on the Vibe Coding Index; Qwen3.8 2.4T A95B has none, so the two cannot be ranked on coding.
Pick Qwen3.8 2.4T A95B for a larger context window (1.05M against 1M tokens) and work measured by AA Coding Index or SciCode, where it leads.
- Shared results
- 7
- Qwen3.7 Max only
- 53
- Qwen3.8 2.4T A95B only
- 2
- Like-for-like categories
- 5 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 Qwen3.7 Max has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B leads, 39.9 against 29.5.
Same board, both measured
Agentic work
AA Agentic Index
Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B leads, 50.1 against 22.5.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only Qwen3.7 Max has a GPQA Diamond result, 90.2%.
Directional only
Knowledge
MMLU Pro
No call
Only Qwen3.7 Max has a MMLU Pro result, 89.3%.
Directional only
Web design
Design Arena: websites
No call
Only Qwen3.7 Max has a Design Arena: websites result, 1274.
Directional only
Long documents
Listed context window
Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3.7 Max
Qwen3.7 Max $0.0037, Qwen3.8 2.4T A95B $0.0050 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Qwen3.7 Max has the number, $4.69.
Directional only
At a glance
- Coding index
- Qwen3.7 Max 54.1 from 3 benchmarks, Qwen3.8 2.4T A95B not benchmarked.
- Widest category
- Agentic work, 27.6 points apart on average over 1 shared benchmark.
- Widest single gap
- AA Agentic Index: Qwen3.7 Max 22.5 against Qwen3.8 2.4T A95B 50.1, 27.6 points apart on a 0 to 100 scale.
- Output price
- Qwen3.7 Max $4.425 against Qwen3.8 2.4T A95B $6.00 per million output tokens, 1.4x apart.
- Context window
- Qwen3.7 Max takes 1M tokens, Qwen3.8 2.4T A95B 1.05M.
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 | Qwen3.7 Max | Bars | Qwen3.8 2.4T A95B | Ties |
|---|---|---|---|---|
| Coding | 0 | 2 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 2 | ||
| General | 0 | 1 | ||
| All shared boards | 0 | 7 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
| Benchmark | Qwen3.7 Max | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| LMArena WebDev | 1515 | Not measured | Only Qwen3.7 Max measured |
| AA Coding Index | 66.0 | 71.9 | Qwen3.8 2.4T A95B |
| LiveCodeBench (Vals AI) | 87.1% | Not measured | Only Qwen3.7 Max measured |
| SWE-bench Verified (Vals AI) | 68.8% | Not measured | Only Qwen3.7 Max measured |
| Vibe Code Bench (Vals AI) | 47.7% | Not measured | Only Qwen3.7 Max measured |
| Code migration (Vals AI) | 13.1% | Not measured | Only Qwen3.7 Max measured |
| Terminal-Bench 2.1 (Vals AI) | 61.0% | Not measured | Only Qwen3.7 Max measured |
| SciCode | 49.5% | 54.1% | Qwen3.8 2.4T A95B |
| Terminal-Bench Hard (Artificial Analysis run) | 50.8% | Not measured | Only Qwen3.7 Max measured |
| ALE-Bench | 1189.4 | Not measured | Only Qwen3.7 Max measured |
| LMArena WebDev: React | 1514 | Not measured | Only Qwen3.7 Max measured |
| LMArena WebDev: HTML | 1512 | Not measured | Only Qwen3.7 Max measured |
| Neither model has a result on the other 31 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3.7 Max | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| AA Intelligence Index | 29.5 | 39.9 | Qwen3.8 2.4T A95B |
| Epoch Capabilities Index | 154.0 | Not measured | Only Qwen3.7 Max measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3.7 Max | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| AA Agentic Index | 22.5 | 50.1 | Qwen3.8 2.4T A95B |
| Design Arena: agents building web apps | 1208 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: agents building full-stack apps | 1191 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: agents building mobile apps | 1154 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: agents building Android apps | 1159 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: agents building Godot games | 1187 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: agents building games | 1161 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: HTML slides | 1098 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: PowerPoint slides | 1169 | Not measured | Only Qwen3.7 Max measured |
| Finance Agent (Vals AI) | 47.8% | Not measured | Only Qwen3.7 Max measured |
| Tax Agent Bench (Vals AI) | 15.8% | Not measured | Only Qwen3.7 Max measured |
| Legal Research Bench (Vals AI) | 25.5% | Not measured | Only Qwen3.7 Max measured |
| Excel Modeling Benchmark (Vals AI) | 57.0% | Not measured | Only Qwen3.7 Max measured |
| τ²-Bench Telecom | 94.7% | Not measured | Only Qwen3.7 Max measured |
| MCP Atlas | Not measured | 84.5% | Only Qwen3.8 2.4T A95B measured |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Qwen3.7 Max | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| GPQA Diamond | 90.2% | Not measured | Only Qwen3.7 Max measured |
| GPQA Diamond (Artificial Analysis run) | 92.3% | 93.5% | Qwen3.8 2.4T A95B |
| Humanity's Last Exam (Artificial Analysis run) | 40.5% | 42.4% | Qwen3.8 2.4T A95B |
| GPQA Diamond (Epoch AI run) | 90.9% | Not measured | Only Qwen3.7 Max measured |
| SimpleBench | 70.4% | Not measured | Only Qwen3.7 Max measured |
| Chess puzzles | 26.0% | Not measured | Only Qwen3.7 Max measured |
| Mystery game puzzles | 32.0% | Not measured | Only Qwen3.7 Max measured |
| EBR-bench | 9.5% | Not measured | Only Qwen3.7 Max measured |
| Neither model has a result on the other 15 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Qwen3.7 Max | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| OTIS Mock AIME | 95.6% | Not measured | Only Qwen3.7 Max measured |
| FrontierMath, tiers 1 to 3 | 64.6% | Not measured | Only Qwen3.7 Max measured |
| FrontierMath, tier 4 | 34.1% | Not measured | Only Qwen3.7 Max measured |
| ProofBench | 26.0% | Not measured | Only Qwen3.7 Max measured |
| MathArena | Not measured | 31.6% | Only Qwen3.8 2.4T A95B measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Qwen3.7 Max | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| MMLU Pro | 89.3% | Not measured | Only Qwen3.7 Max measured |
| LegalBench (Vals AI) | 84.9% | Not measured | Only Qwen3.7 Max measured |
| CorpFin (Vals AI) | 63.7% | Not measured | Only Qwen3.7 Max measured |
| TaxEval (Vals AI) | 75.3% | Not measured | Only Qwen3.7 Max measured |
| MedCode (Vals AI) | 38.8% | Not measured | Only Qwen3.7 Max measured |
| SimpleQA Verified | 55.8% | Not measured | Only Qwen3.7 Max measured |
| Neither model has a result on the other 14 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Qwen3.7 Max | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| Design Arena: websites | 1274 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: UI components | 1267 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: game dev | 1265 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: data viz | 1276 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: 3D | 1265 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: all code categories | 1275 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: SVG | 1216 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: ASCII art | 1211 | Not measured | Only Qwen3.7 Max measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3.7 Max | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | 79.4% | Not measured | Only Qwen3.7 Max measured |
| IFBench | 80.5% | Not measured | Only Qwen3.7 Max measured |
| Long context reasoning (AA-LCR) | 79.0% | 80.3% | Qwen3.8 2.4T A95B |
| DTBench | 92.3% | Not measured | Only Qwen3.7 Max measured |
| LMCA | 44.0% | Not measured | Only Qwen3.7 Max measured |
| EQ-Bench 4 | 1110 | Not measured | Only Qwen3.7 Max measured |
| Neither model has a result on the other 42 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3.7 Max | Qwen3.8 2.4T A95B | 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
Qwen3.7 Max costs less
Repository review
50K input + 3K output tokens
Qwen3.7 Max costs less
Agent loop
200K input + 10K output tokens
Qwen3.7 Max 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 | Qwen3.7 Max | Qwen3.8 2.4T A95B |
|---|---|---|
| Maker | Qwen | Qwen |
| Weights | No public weights listed | Open weights |
| Released | May 21, 2026 | August 12, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $1.475 | $2.00 |
| Output $/Mtok | $4.425 | $6.00 |
| Coding index | 54.1 | Not benchmarked |
| Independent measurements behind it | 3 | 0 |
| Cost per solved task | $4.69 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3.7 Max better than Qwen3.8 2.4T A95B for coding?
Only Qwen3.7 Max has a coding score, 54.1 on the Vibe Coding Index; Qwen3.8 2.4T A95B has none, so the two cannot be ranked on coding. Pick Qwen3.8 2.4T A95B for a larger context window (1.05M against 1M tokens) and work measured by AA Coding Index or SciCode, where it leads.
Which is cheaper, Qwen3.7 Max or Qwen3.8 2.4T A95B?
Qwen3.7 Max costs $1.475 per million input tokens and $4.425 per million output tokens; Qwen3.8 2.4T A95B costs $2.00 and $6.00. Cost per solved task is known for Qwen3.7 Max only.
Which has the bigger context window, Qwen3.7 Max or Qwen3.8 2.4T A95B?
Qwen3.8 2.4T A95B, with 1.05M tokens against 1M.
How many benchmarks is the Qwen3.7 Max vs Qwen3.8 2.4T A95B comparison based on?
7 benchmarks have a result for both models as of October 22, 2026. Qwen3.7 Max's coding index rests on 3 independent benchmarks and Qwen3.8 2.4T A95B's on 0. Where only one model has a result, the page says so instead of naming a winner.