Qwen3.8 27B vs Spark X2.6 4B, head to head

Side A

Side B

Overall

Qwen3.8 27B is clearly better. It wins 76 of the 84 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. Spark X2.6 4B spends 1.3× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskAQwen3.8 27BBSpark X2.6 4BQwen3.8 27BSpark X2.6 4B

Overall

4833.3s

5.9K8.2K

151m 3s

Agents

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

5736.6s

5.2K11.5K

141m 32s

Structured Extraction

Turns logs, diffs and records into exact JSON

7320.6s

4.6K5.3K

1039.5s

Coding

Writes code and SQL that pass hidden tests

3753.0s

9.3K9.1K

41m 8s

Grounded Answers

Answers from the given documents with sources, never guesses

6131.6s

4.2K6.6K

1050.2s

Instruction Following

Applies every rule, including ones changed mid-conversation

6733.6s

6.9K11.9K

371m 29s

Business Logic

Computes billing, scheduling and pricing rules exactly

3632.9s

7.6K4.9K

1036.3s

Security & permissions

Ignores planted instructions, still does the allowed work

5122.6s

3.7K7K

3154.3s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

040.0s

5.9K11.6K

01m 30s

What you'd run

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

SpecAQwen3.8 27BBSpark X2.6 4B

Speed

196 tok/s

136 tok/s

Machine

Hosted

RTX 5090, 32 GB

Memory at 32K

—

9.4 GB

Context

256K

605K

Cost per run

$1.28

$1.61 est.

Cost per case

$0.0083

$0.011 est.

Time per case

33.3s

1m 3s

Quantization

FP8

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.

Qwen3.8 27BSpark X2.6 4B

Every test case

153 test cases

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

Agents100

Structured Extraction182

Coding100

Grounded Answers120

Instruction Following103

Business Logic81

Security & permissions82

Diagnosis & investigation00

76 won by Qwen3.8 27B8 won by Spark X2.6 4B69 tied