Muse Spark 1.2 vs Muse Spark 1.3

$0.97 / task
Wins 0 of 6 benchmarks
$1.37 / task
Wins 4 of 6 benchmarks
Terminal-Bench 4.0 Terminal-Bench 4.0 · source setting 2: Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite
Muse Spark 1.27.1
Muse Spark 1.316.7
DeepSWE 1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition
Muse Spark 1.254.9
Muse Spark 1.3 · xhigh67.8
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool
Muse Spark 1.21,534
Muse Spark 1.31,621
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math)
Muse Spark 1.257.4
Muse Spark 1.359.7
FrontierCode 1.1 FrontierCode 1.1: Agents implement changes in real repositories, graded against maintainer-defined requirements
Muse Spark 1.2—
Muse Spark 1.3 · max40.6
Terminal-Bench Science 0.1 Terminal-Bench Science 0.1: Agents complete expert-authored research workflows across five scientific domains in a terminal
Muse Spark 1.2—
Muse Spark 1.3 · max11

Specs

SpecMuse Spark 1.2Muse Spark 1.3
Input, per 1M$1.25$1.25
Output, per 1M$4.25$4.25
Cost per task?$0.97$1.37
Speed, tok/s355273
Context1M1M
WeightsClosedClosed
ReleasedAug 2026Sep 2026
See images✓✓
Read PDFs✓✓
Hear audio——
Watch video✓✓
Call tools✓✓
Force a tool call——
Return strict JSON✓✓
Search the web✓✓
Run code??
Use a computer??

What breaks when you switch

Muse Spark 1.2 → Muse Spark 1.3
Only auto tool_choice is supported›

tool_choice none, required or a named function returns HTTP 400; use auto and handle either a tool call or text.

Search filters return HTTP 400 · Messages API›

allowed_domains, blocked_domains and max_uses return HTTP 400 on Messages search grounding; omit them and use the supported web_search tool.

Manual budget does not set effort · Messages API›

Compatibility budget_tokens does not set reasoning effort; use output_config.effort for depth control.

No Chat Completions search grounding · Chat Completions›

Search grounding is unavailable in Chat Completions; use Responses or Messages.

Reasoning cannot be disabled›

Muse Wonder and Muse Spark do not support disabling reasoning with none; keep reasoning enabled.

Private reasoning still costs tokens›

Private reasoning consumes the output budget and billed output tokens; budget for it even though it is absent from the response body.

Muse Spark 1.3 → Muse Spark 1.2
Only auto tool_choice is supported›

tool_choice none, required or a named function returns HTTP 400; use auto and handle either a tool call or text.

Reasoning cannot be disabled›

Muse Wonder and Muse Spark do not support disabling reasoning with none; keep reasoning enabled.