Muse Spark 1.3 Contributor vs Qwen3.8 27B, head to head

Side A

Side B

Overall

Muse Spark 1.3 Contributor is clearly better. It wins 59 of the 68 test cases where they differ.

Learn to build evals like this in the AI Engineering Academy

Task by task

A score turns orange only when that model wins clearly more of the task's test cases. Under each score, the average time per test case on the machine it ran on. Muse Spark 1.3 Contributor spends 1.5× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskAMuse Spark 1.3 ContributorBQwen3.8 27BMuse Spark 1.3 ContributorQwen3.8 27B

Overall

661m 42s

8.7K5.9K

4833.3s

Agents

Runs multi-step jobs through tools, within a written policy

573m 16s

14.7K5.2K

5736.6s

Structured Extraction

Turns logs, diffs and records into exact JSON

9037.9s

4.2K4.6K

7320.6s

Coding

Writes code and SQL that pass hidden tests

482m 1s

10.8K9.3K

3753.0s

Grounded Answers

Answers from the given documents with sources, never guesses

811m 1s

6.1K4.2K

6131.6s

Instruction Following

Applies every rule, including ones changed mid-conversation

841m 18s

8.7K6.9K

6733.6s

Business Logic

Computes billing, scheduling and pricing rules exactly

761m 7s

6K7.6K

3632.9s

Security & permissions

Ignores planted instructions, still does the allowed work

761m 59s

8.2K3.7K

5122.6s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

173m 34s

17.2K5.9K

040.0s

What you'd run

The build behind each score. Orange marks the faster, smaller, cheaper or longer-context side.

SpecAMuse Spark 1.3 ContributorBQwen3.8 27B

Speed

107 tok/s

196 tok/s

Machine

Hosted

Memory at 32K

—

Context

256K

Cost per run

$0.41

$1.28

Cost per case

$0.0027

$0.0083

Time per case

1m 42s

33.3s

Quantization

—

FP8

Harness

openrouter

The race

3 lead changes

Each model's running score as the test cases go by. The dashed line is a perfect run.

Muse Spark 1.3 ContributorQwen3.8 27B

Every test case

153 test cases

Each square is one test case, colored by the model that scored higher.

Agents32

Structured Extraction111

Coding52

Grounded Answers81

Instruction Following102

Business Logic141

Security & permissions70

Diagnosis & investigation10

59 won by Muse Spark 1.3 Contributor9 won by Qwen3.8 27B85 tied