Saba vs Extract
Updated October 21, 2026. 0 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
- Coding
- No data
- Overall
- 6.5
- Output $/M
- $0.60
- Coding
- No data
- Overall
- No data
- Output $/M
- No data
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
Compare them on price, context and the boards below.
- Shared results
- 0
- Saba only
- 4
- Extract only
- 0
- Like-for-like categories
- 0 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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 Saba has a AA Intelligence Index result, 6.5.
Directional only
Long documents
Listed context window
Extract
Extract takes 1M tokens against 33K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Extract
Saba $0.0005, Extract $0.0000 per turn.
List prices
At a glance
- Coding index
- Saba not benchmarked, Extract not benchmarked.
- Widest category
- No category has a result for both models.
- Widest single gap
- No benchmark has a result for both models.
- Output price
- Saba $0.60 against Extract Free per million output tokens.
- Context window
- Saba takes 33K tokens, Extract 1M.
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.
CodingNot comparableSix of these boards feed the Vibe Coding Index0 boards, none shared
| Benchmark | Saba | Extract | Leader |
|---|---|---|---|
| Neither model has a result on 38 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Saba | Extract | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.5 | Not measured | Only Saba measured |
| Neither model has a result on the other 1 board here | |||
Agentic workNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Saba | Extract | Leader |
|---|---|---|---|
| Neither model has a result on 39 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Saba | Extract | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 42.4% | Not measured | Only Saba measured |
| Humanity's Last Exam (Artificial Analysis run) | 4.3% | Not measured | Only Saba measured |
| Neither model has a result on the other 19 boards here | |||
MathNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Saba | Extract | Leader |
|---|---|---|---|
| Neither model has a result on 13 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Saba | Extract | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 61.1% | Not measured | Only Saba measured |
| Neither model has a result on the other 16 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Saba | Extract | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Saba | Extract | Leader |
|---|---|---|---|
| Neither model has a result on 46 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Saba | Extract | 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
Extract costs less
Repository review
50K input + 3K output tokens
Extract costs less
Agent loop
200K input + 10K output tokens
Extract 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 | Mistral Saba | ScaleDown Extract |
|---|---|---|
| Maker | Mistral AI | Scaledown |
| Weights | No public weights listed | No public weights listed |
| Released | February 17, 2025 | October 13, 2026 |
| Context window | 33K | 1M |
| Input $/Mtok | $0.20 | $0.04 |
| Output $/Mtok | $0.60 | Free |
| 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 Saba better than Extract for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Compare them on price, context and the boards below.
Which is cheaper, Saba or Extract?
Saba costs $0.20 per million input tokens and $0.60 per million output tokens; Extract costs $0.04 and Free. Cost per solved task is known for neither of them.
Which has the bigger context window, Saba or Extract?
Extract, with 1M tokens against 33K.
How many benchmarks is the Saba vs Extract comparison based on?
0 benchmarks have a result for both models as of October 21, 2026. Saba's coding index rests on 0 independent benchmarks and Extract's on 0. Where only one model has a result, the page says so instead of naming a winner.