Mellum2.1-12B-A2.5B-Thinking

JetBrainsOpen weightsReasoningReleased Oct 8, 2026

Compare with Claude Opus 5.5 Source scores ↗

Overall score

—

Not enough evidence to rank yet

Context window

128K

128,000 tokens

Price per 1M tokens

— in · — out

No price listed

Blended price

—

3:1 input:output tokens

Output speed

—

Not measured yet

Category scores

Scores per capability area with the model's rank among ranked models in that category.

1Coding20.6

Higher is better. #N is the model's rank in that category, where it is eligible to be ranked.

Benchmark results (6)

As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.

Coding

SWE-bench Verified	47.0	#89 of 98
SWE-bench Pro	28.0	#67 of 69
LiveCodeBench v6	82.0	#22 of 46

Agentic & tool use

Terminal-Bench 2.1

17.4

#67 of 68

Knowledge

MMLU-Redux

87.8

#11 of 15

Instruction following

IFEval

90.6

#21 of 53

Pricing by source

USD per 1M tokens.

Source	Input	Output	Cached in
List price	—	—	—

Apache 2.0 open weights for self-hosted inference. Zero token rates represent no provider token fee; hardware and hosting costs still apply. JetBrains does not publish a hosted API token rate for this checkpoint.

Speed

Measured by us through OpenRouter (median of trials).

Not available on OpenRouter, so we cannot measure it yet.