Sonar vs Sakana Namazu
Sonar costs 4.0x less per output token than Sakana Namazu ($1.00 vs $4.00 per million). Updated October 22, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $1.00
- Coding
- No data
- Overall
- No data
- Output $/M
- $4.00
Sonar or Sakana Namazu: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Sonar for output tokens 4.0x cheaper ($1.00 vs $4.00 per million).
No benchmark has tested both yet. Sonar has results on LiveCodeBench (Artificial Analysis run), AA Intelligence Index and GPQA Diamond (Artificial Analysis run); Sakana Namazu 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 Sonar has a AA Intelligence Index result, 7.7.
Directional only
Long documents
Listed context window
Sakana Namazu
Sakana Namazu takes 262K tokens against 127K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Sonar
Sonar $0.0015, Sakana Namazu $0.0029 per turn.
List prices
At a glance
- Coding index
- Sonar not benchmarked, Sakana Namazu 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
- Sonar $1.00 against Sakana Namazu $4.00 per million output tokens, 4.0x apart.
- Context window
- Sonar takes 127K tokens, Sakana Namazu 262K.
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 Index1 board measured
| Benchmark | Sonar | Sakana Namazu | Leader |
|---|---|---|---|
| LiveCodeBench (Artificial Analysis run) | 29.5% | Not measured | Only Sonar measured |
| Neither model has a result on the other 42 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Sonar | Sakana Namazu | Leader |
|---|---|---|---|
| AA Intelligence Index | 7.7 | Not measured | Only Sonar measured |
| Neither model has a result on the other 1 board here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Sonar | Sakana Namazu | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 47.1% | Not measured | Only Sonar measured |
| Humanity's Last Exam (Artificial Analysis run) | 4.9% | Not measured | Only Sonar measured |
| Neither model has a result on the other 21 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Sonar | Sakana Namazu | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 68.9% | Not measured | Only Sonar measured |
| Neither model has a result on the other 19 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
Sonar costs less
Repository review
50K input + 3K output tokens
Sonar costs less
Agent loop
200K input + 10K output tokens
Sonar 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 | Perplexity Sonar | Sakana Namazu |
|---|---|---|
| Maker | Perplexity | Sakana |
| Weights | No public weights listed | No public weights listed |
| Released | January 27, 2025 | August 11, 2026 |
| Context window | 127K | 262K |
| Input $/Mtok | $1.00 | $0.95 |
| Output $/Mtok | $1.00 | $4.00 |
| 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 Sonar better than Sakana Namazu for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Sonar for output tokens 4.0x cheaper ($1.00 vs $4.00 per million).
Which is cheaper, Sonar or Sakana Namazu?
Sonar costs $1.00 per million input tokens and $1.00 per million output tokens; Sakana Namazu costs $0.95 and $4.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Sonar or Sakana Namazu?
Sakana Namazu, with 262K tokens against 127K.
Has any benchmark tested both Sonar and Sakana Namazu?
No benchmark has tested both yet. Sonar has results on LiveCodeBench (Artificial Analysis run), AA Intelligence Index and GPQA Diamond (Artificial Analysis run); Sakana Namazu has none yet. Compare them on price and context instead. Data as of October 22, 2026.