Muse Spark 1.3 Contributor vs Spark X2.6 4B, head to head

Side A

Side B

Overall

Muse Spark 1.3 Contributor is clearly better. It wins 93 of the 94 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 1.2× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskAMuse Spark 1.3 ContributorBSpark X2.6 4BMuse Spark 1.3 ContributorSpark X2.6 4B

Overall

661m 42s

8.7K8.2K

151m 3s

Agents

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

573m 16s

14.7K11.5K

141m 32s

Structured Extraction

Turns logs, diffs and records into exact JSON

9037.9s

4.2K5.3K

1039.5s

Coding

Writes code and SQL that pass hidden tests

482m 1s

10.8K9.1K

41m 8s

Grounded Answers

Answers from the given documents with sources, never guesses

811m 1s

6.1K6.6K

1050.2s

Instruction Following

Applies every rule, including ones changed mid-conversation

841m 18s

8.7K11.9K

371m 29s

Business Logic

Computes billing, scheduling and pricing rules exactly

761m 7s

6K4.9K

1036.3s

Security & permissions

Ignores planted instructions, still does the allowed work

761m 59s

8.2K7K

3154.3s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

173m 34s

17.2K11.6K

01m 30s

What you'd run

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

SpecAMuse Spark 1.3 ContributorBSpark X2.6 4B

Speed

107 tok/s

136 tok/s

Machine

Hosted

RTX 5090, 32 GB

Memory at 32K

—

9.4 GB

Context

605K

Cost per run

$0.41

$1.61 est.

Cost per case

$0.0027

$0.011 est.

Time per case

1m 42s

1m 3s

Quantization

—

BF16

Harness

openrouter

llama.cpp

The race

No lead changes

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

Muse Spark 1.3 ContributorSpark X2.6 4B

Every test case

153 test cases

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

Agents100

Structured Extraction181

Coding100

Grounded Answers150

Instruction Following130

Business Logic140

Security & permissions120

Diagnosis & investigation10

93 won by Muse Spark 1.3 Contributor1 won by Spark X2.6 4B59 tied