Enter opens the highlighted result. Esc closes.

Saba vs Hermes 4 405B

Hermes 4 405B leads Saba on the Artificial Analysis Intelligence Index, 7.5 to 6.5, and Saba costs 5.0x less per output token ($0.60 vs $3.00 per million). Updated October 22, 2026; 1 benchmarks have a result for both.

SabaMistral AI
Coding
No data
Overall
No data
Output $/M
$0.60
0
N Hermes 4 405BNous Research
Coding
No data
Overall
No data
Output $/M
$3.00
1
vs boards won of 1 shared

Saba or Hermes 4 405B: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick Saba for output tokens 5.0x cheaper ($0.60 vs $3.00 per million) and work measured by AA Intelligence Index, where it leads.

Shared results
1
Saba only
3
Hermes 4 405B only
1
Like-for-like categories
1 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.

At a glance

Coding index
Saba not benchmarked, Hermes 4 405B not benchmarked.
Widest category
Intelligence, 1.0 points apart on average over 1 shared benchmark.
Widest single gap
AA Intelligence Index: Saba 6.5 against Hermes 4 405B 7.5, 1.0 points apart on a 0 to 100 scale.
Output price
Saba $0.60 against Hermes 4 405B $3.00 per million output tokens, 5.0x apart.
Context window
Saba takes 33K tokens, Hermes 4 405B 131K.

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.

Boards won, where both have a result
CategorySabaBarsHermes 4 405BTies
Intelligence01
All shared boards01
CodingNot comparableSix of these boards feed the Vibe Coding Index0 boards, none shared
Coding benchmarks for Saba and Hermes 4 405B
BenchmarkSabaHermes 4 405BLeader
Neither model has a result on 39 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Saba and Hermes 4 405B
BenchmarkSabaHermes 4 405BLeader
AA Intelligence Index6.57.5Hermes 4 405B
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
Agentic work benchmarks for Saba and Hermes 4 405B
BenchmarkSabaHermes 4 405BLeader
Neither model has a result on 41 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Reasoning benchmarks for Saba and Hermes 4 405B
BenchmarkSabaHermes 4 405BLeader
GPQA Diamond (Artificial Analysis run)42.4%Not measuredOnly Saba measured
Humanity's Last Exam (Artificial Analysis run)4.3%Not measuredOnly Saba measured
Kagi LLM BenchmarkNot measured55.8%Only Hermes 4 405B 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
Math benchmarks for Saba and Hermes 4 405B
BenchmarkSabaHermes 4 405BLeader
Neither model has a result on 13 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Knowledge benchmarks for Saba and Hermes 4 405B
BenchmarkSabaHermes 4 405BLeader
MMLU Pro (Artificial Analysis run)61.1%Not measuredOnly Saba measured
Neither model has a result on the other 17 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Saba and Hermes 4 405B
BenchmarkSabaHermes 4 405BLeader
Neither model has a result on 9 boards here
GeneralNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
General benchmarks for Saba and Hermes 4 405B
BenchmarkSabaHermes 4 405BLeader
Neither model has a result on 46 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Saba and Hermes 4 405B
BenchmarkSabaHermes 4 405BLeader
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

Saba$0.0005Fits in one request
Hermes 4 405B$0.0025Fits in one request

Saba costs less

Repository review

50K input + 3K output tokens

Saba$0.012Exceeds the context window
Hermes 4 405B$0.059Fits in one request

Saba costs less

Agent loop

200K input + 10K output tokens

Saba$0.046Exceeds the context window
Hermes 4 405B$0.230Exceeds the context window

Saba 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.

Specifications of Saba and Hermes 4 405B
SpecificationMistral SabaNous Hermes 4 405B
MakerMistral AINous Research
WeightsNo public weights listedOpen weights
ReleasedFebruary 17, 2025August 26, 2025
Context window33K131K
Input $/Mtok$0.20$1.00
Output $/Mtok$0.60$3.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Saba better than Hermes 4 405B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Saba for output tokens 5.0x cheaper ($0.60 vs $3.00 per million) and work measured by AA Intelligence Index, where it leads.

Which is cheaper, Saba or Hermes 4 405B?

Saba costs $0.20 per million input tokens and $0.60 per million output tokens; Hermes 4 405B costs $1.00 and $3.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Saba or Hermes 4 405B?

Hermes 4 405B, with 131K tokens against 33K.

How many benchmarks is the Saba vs Hermes 4 405B comparison based on?

1 benchmarks have a result for both models as of October 22, 2026. Saba's coding index rests on 0 independent benchmarks and Hermes 4 405B's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next