Qwen3 Next 80B A3B Instruct vs Skyfall 36B V2
Skyfall 36B V2 costs 1.4x less per output token than Qwen3 Next 80B A3B Instruct ($0.80 vs $1.10 per million). Updated October 22, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $1.10
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.80
Qwen3 Next 80B A3B Instruct or Skyfall 36B V2: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Qwen3 Next 80B A3B Instruct for a larger context window (262K against 33K tokens).
No benchmark has tested both yet. Qwen3 Next 80B A3B Instruct has results on LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run) and LMArena Text: coding; Skyfall 36B V2 has none yet. Compare them on price and context instead.
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
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
No call
Only Qwen3 Next 80B A3B Instruct has a AA Intelligence Index result, 9.6.
Directional only
Long documents
Listed context window
Qwen3 Next 80B A3B Instruct
Qwen3 Next 80B A3B Instruct takes 262K tokens against 33K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3 Next 80B A3B Instruct
Qwen3 Next 80B A3B Instruct $0.0006, Skyfall 36B V2 $0.0009 per turn.
List prices
At a glance
- Coding index
- Qwen3 Next 80B A3B Instruct not benchmarked, Skyfall 36B V2 not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- Qwen3 Next 80B A3B Instruct $1.10 against Skyfall 36B V2 $0.80 per million output tokens, 1.4x apart.
- Context window
- Qwen3 Next 80B A3B Instruct takes 262K tokens, Skyfall 36B V2 33K.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index4 boards measured
| Benchmark | Qwen3 Next 80B A3B Instruct | Skyfall 36B V2 | Leader |
|---|---|---|---|
| LiveCodeBench (Artificial Analysis run) | 78.4% | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| Terminal-Bench Hard (Artificial Analysis run) | 9.8% | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: coding | 1440 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: software and IT | 1447 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| Neither model has a result on the other 39 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Qwen3 Next 80B A3B Instruct | Skyfall 36B V2 | Leader |
|---|---|---|---|
| AA Intelligence Index | 9.6 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Qwen3 Next 80B A3B Instruct | Skyfall 36B V2 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 41.5% | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| Neither model has a result on the other 41 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index6 boards measured
| Benchmark | Qwen3 Next 80B A3B Instruct | Skyfall 36B V2 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 75.9% | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| Humanity's Last Exam (Artificial Analysis run) | 12.6% | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: hard prompts | 1428 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: expert | 1417 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: hard prompts in English | 1431 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| Kagi LLM Benchmark | 66.7% | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| Neither model has a result on the other 17 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
| Benchmark | Qwen3 Next 80B A3B Instruct | Skyfall 36B V2 | Leader |
|---|---|---|---|
| AA Math Index | 84.3 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| AIME 2025 (Artificial Analysis run) | 84.3% | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: math | 1440 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: mathematical work | 1434 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| Neither model has a result on the other 10 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | Qwen3 Next 80B A3B Instruct | Skyfall 36B V2 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 82.4% | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: science | 1434 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: medicine and healthcare | 1455 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: legal and government | 1431 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: business and finance | 1422 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| Neither model has a result on the other 15 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index20 boards measured
| Benchmark | Qwen3 Next 80B A3B Instruct | Skyfall 36B V2 | Leader |
|---|---|---|---|
| IFBench | 60.7% | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| Long context reasoning (AA-LCR) | 63.7% | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| Fiction.LiveBench | 55.6% | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text | 1417 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: instruction following | 1388 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: creative writing | 1333 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: English | 1421 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: non-English | 1407 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: Chinese | 1460 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: German | 1416 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: Japanese | 1395 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: Korean | 1363 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: French | 1414 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: Spanish | 1435 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: Russian | 1404 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: Polish | 1398 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: multi-turn | 1416 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: longer queries | 1402 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: writing and language | 1355 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| LMArena Text: entertainment and media | 1349 | Not measured | Only Qwen3 Next 80B A3B Instruct measured |
| Neither model has a result on the other 28 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 Next 80B A3B Instruct costs less
Repository review
50K input + 3K output tokens
Qwen3 Next 80B A3B Instruct costs less
Agent loop
200K input + 10K output tokens
Qwen3 Next 80B A3B Instruct 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 Next 80B A3B Instruct | TheDrummer Skyfall 36B V2 |
|---|---|---|
| Maker | Qwen | TheDrummer |
| Weights | Open weights | Open weights |
| Released | September 11, 2025 | March 10, 2025 |
| Context window | 262K | 33K |
| Input $/Mtok | $0.10 | $0.55 |
| Output $/Mtok | $1.10 | $0.80 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3 Next 80B A3B Instruct better than Skyfall 36B V2 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Qwen3 Next 80B A3B Instruct for a larger context window (262K against 33K tokens).
Which is cheaper, Qwen3 Next 80B A3B Instruct or Skyfall 36B V2?
Qwen3 Next 80B A3B Instruct costs $0.10 per million input tokens and $1.10 per million output tokens; Skyfall 36B V2 costs $0.55 and $0.80. Cost per solved task is known for neither of them.
Which has the bigger context window, Qwen3 Next 80B A3B Instruct or Skyfall 36B V2?
Qwen3 Next 80B A3B Instruct, with 262K tokens against 33K.
Has any benchmark tested both Qwen3 Next 80B A3B Instruct and Skyfall 36B V2?
No benchmark has tested both yet. Qwen3 Next 80B A3B Instruct has results on LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run) and LMArena Text: coding; Skyfall 36B V2 has none yet. Compare them on price and context instead. Data as of October 22, 2026.