Qwen3.6 27B vs Fugu Ultra v2
Qwen3.6 27B costs 11.1x less per output token than Fugu Ultra v2 ($2.70 vs $30.00 per million). Updated October 23, 2026; no benchmark has tested both models yet.
- Coding
- 36.8
- Overall
- 45.3
- Output $/M
- $2.70
- Coding
- No data
- Overall
- No data
- Output $/M
- $30.00
Qwen3.6 27B or Fugu Ultra v2: which to pick
Only Qwen3.6 27B has a coding score, 36.8 on the Vibe Coding Index; Fugu Ultra v2 has none, so the two cannot be ranked on coding.
Pick Fugu Ultra v2 for a larger context window (1M against 262K tokens).
No benchmark has tested both yet. Qwen3.6 27B has results on AA Coding Index, SWE-bench Verified (Vals AI) and Vibe Code Bench (Vals AI); Fugu Ultra 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
Only Qwen3.6 27B has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
No call
Only Qwen3.6 27B has a AA Intelligence Index result, 21.4.
Directional only
Agentic work
AA Agentic Index
No call
Only Qwen3.6 27B has a AA Agentic Index result, 18.5.
Directional only
Long documents
Listed context window
Fugu Ultra v2
Fugu Ultra v2 takes 1M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3.6 27B
Qwen3.6 27B $0.0018, Fugu Ultra v2 $0.020 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Qwen3.6 27B has the number, $1.30.
Directional only
At a glance
- Coding index
- Qwen3.6 27B 36.8 from 2 benchmarks, Fugu Ultra 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
- Qwen3.6 27B $2.70 against Fugu Ultra v2 $30.00 per million output tokens, 11.1x apart.
- Context window
- Qwen3.6 27B takes 262K tokens, Fugu Ultra v2 1M.
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 Index5 boards measured
| Benchmark | Qwen3.6 27B | Fugu Ultra v2 | Leader |
|---|---|---|---|
| AA Coding Index | 53.7 | Not measured | Only Qwen3.6 27B measured |
| SWE-bench Verified (Vals AI) | 70.0% | Not measured | Only Qwen3.6 27B measured |
| Vibe Code Bench (Vals AI) | 11.9% | Not measured | Only Qwen3.6 27B measured |
| SciCode | 42.8% | Not measured | Only Qwen3.6 27B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 34.8% | Not measured | Only Qwen3.6 27B measured |
| Neither model has a result on the other 38 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Qwen3.6 27B | Fugu Ultra v2 | Leader |
|---|---|---|---|
| AA Intelligence Index | 21.4 | Not measured | Only Qwen3.6 27B measured |
| Epoch Capabilities Index | 146.2 | Not measured | Only Qwen3.6 27B measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Qwen3.6 27B | Fugu Ultra v2 | Leader |
|---|---|---|---|
| AA Agentic Index | 18.5 | Not measured | Only Qwen3.6 27B measured |
| τ²-Bench Telecom | 94.2% | Not measured | Only Qwen3.6 27B measured |
| Neither model has a result on the other 40 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
| Benchmark | Qwen3.6 27B | Fugu Ultra v2 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 84.2% | Not measured | Only Qwen3.6 27B measured |
| Humanity's Last Exam (Artificial Analysis run) | 23.1% | Not measured | Only Qwen3.6 27B measured |
| GPQA Diamond (Epoch AI run) | 85.9% | Not measured | Only Qwen3.6 27B measured |
| Mystery game puzzles | 7.0% | Not measured | Only Qwen3.6 27B measured |
| Neither model has a result on the other 19 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Qwen3.6 27B | Fugu Ultra v2 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 91.1% | Not measured | Only Qwen3.6 27B measured |
| FrontierMath, tiers 1 to 3 | 35.1% | Not measured | Only Qwen3.6 27B measured |
| Neither model has a result on the other 12 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
| Benchmark | Qwen3.6 27B | Fugu Ultra v2 | Leader |
|---|---|---|---|
| CaseLaw (Vals AI) | 53.2% | Not measured | Only Qwen3.6 27B measured |
| CorpFin (Vals AI) | 62.3% | Not measured | Only Qwen3.6 27B measured |
| TaxEval (Vals AI) | 71.3% | Not measured | Only Qwen3.6 27B measured |
| MortgageTax (Vals AI) | 68.3% | Not measured | Only Qwen3.6 27B measured |
| Neither model has a result on the other 16 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index6 boards measured
| Benchmark | Qwen3.6 27B | Fugu Ultra v2 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 45.6% | Not measured | Only Qwen3.6 27B measured |
| IFBench | 67.6% | Not measured | Only Qwen3.6 27B measured |
| Long context reasoning (AA-LCR) | 77.3% | Not measured | Only Qwen3.6 27B measured |
| DTBench | 78.1% | Not measured | Only Qwen3.6 27B measured |
| LMCA | 34.5% | Not measured | Only Qwen3.6 27B measured |
| EQ-Bench 4 | 1026 | Not measured | Only Qwen3.6 27B measured |
| Neither model has a result on the other 42 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
Qwen3.6 27B costs less
Repository review
50K input + 3K output tokens
Qwen3.6 27B costs less
Agent loop
200K input + 10K output tokens
Qwen3.6 27B 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 | Qwen3.6 27B | Sakana Fugu Ultra v2 |
|---|---|---|
| Maker | Qwen | Sakana |
| Weights | Open weights | No public weights listed |
| Released | April 27, 2026 | September 11, 2026 |
| Context window | 262K | 1M |
| Input $/Mtok | $0.45 | $5.00 |
| Output $/Mtok | $2.70 | $30.00 |
| Coding index | 36.8 | Not benchmarked |
| Independent measurements behind it | 2 | 0 |
| Cost per solved task | $1.30 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3.6 27B better than Fugu Ultra v2 for coding?
Only Qwen3.6 27B has a coding score, 36.8 on the Vibe Coding Index; Fugu Ultra v2 has none, so the two cannot be ranked on coding. Pick Fugu Ultra v2 for a larger context window (1M against 262K tokens).
Which is cheaper, Qwen3.6 27B or Fugu Ultra v2?
Qwen3.6 27B costs $0.45 per million input tokens and $2.70 per million output tokens; Fugu Ultra v2 costs $5.00 and $30.00. Cost per solved task is known for Qwen3.6 27B only.
Which has the bigger context window, Qwen3.6 27B or Fugu Ultra v2?
Fugu Ultra v2, with 1M tokens against 262K.
Has any benchmark tested both Qwen3.6 27B and Fugu Ultra v2?
No benchmark has tested both yet. Qwen3.6 27B has results on AA Coding Index, SWE-bench Verified (Vals AI) and Vibe Code Bench (Vals AI); Fugu Ultra v2 has none yet. Compare them on price and context instead. Data as of October 23, 2026.