Mellum2.1 Thinking

Released
2026-10-08
Last refreshed
2026-10-08
Status
Researched today
Open sourceCommercial use: permittedCodingRAGAgentsLong contextJSON / Tool use

Mellum2.1 Thinking is available now for coding, rag, and agents with open-source and 131k context; evaluate it while provider pricing coverage matures.

JetBrains releases · 2 in the last 12 monthsChangelog →
Specifications
Family
Mellum 2
Released
2026-10-08
Context
131k
Parameters
12B (2.5B active)
Architecture
Mixture of Experts
Specialization
code
Openness
Open source
License
Apache 2.0OSI-approvedCommercial use: permitted
Weights
Available
Code
Unknown
Training
Fine-tuned
Created by
JetBrains

Developer tools company building code-specialized Mellum models.

Prague, Czech Republic
Founded 2000
Website
Pricing

No tracked provider token pricing is available yet.

Links
Website HuggingFace

About

Mellum2.1 Thinking is JetBrains' 2026-10-08 open-weight upgrade of Mellum2: same 12B MoE / 2.5B active / 131K context architecture, with much heavier reinforcement learning in real repositories for agentic coding, tool use, math, and reasoning. Apache 2.0. JetBrains reports large gains on SWE-bench Verified (47.0 vs 2.0 for Mellum2 Thinking under the same Pi harness) and LiveCodeBench v6 (82.0). Serve with vLLM (reasoning-parser qwen3; optional Hermes tool calling). GGUF/MTP heads coming soon per the card. Open weights on Hugging Face; not listed as a hosted JetBrains API model.

Provider price ladder

No tracked provider token pricing is available for this model yet.

Capabilities

ReasoningJSON / Tool use

Benchmark peer barsfor Coding

SWE-bench ProRank 48 of 49
Claude Fable 5
80.3
Claude Opus 5
79.2
Claude Opus 4.8
69.2
Qwen3.8-Max
67.7
Mellum2.1 Thinkingcurrent
28.0
SWE-bench VerifiedRank 88 of 90
Claude Fable 5
96.0
Claude Opus 5
96.0
Claude Mythos Preview
93.9
Claude Opus 4.8
88.6
Mellum2.1 Thinkingcurrent
47.0
LiveCodeBenchRank 25 of 67
DeepSeek V4 Pro
93.5
Gemini 3.1 Pro Preview
91.7
DeepSeek V4 Flash
91.6
Qwen3.7-Max
91.6
Mellum2.1 Thinkingcurrent
82.0

Benchmark scores(7)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
LiveCodeBench82.0—Observed 2026-10-08—Source
HumanEval+91.5—Observed 2026-10-08—Source
SWE-bench Verified47.0—Observed 2026-10-08—Source
Terminal-Bench 2.117.4—Observed 2026-10-08—Source
SWE-bench Pro28.0—Observed 2026-10-08—Source
Instruction-Following Evaluation90.6—Observed 2026-10-08—Source
Google-Proof Q&A64.6—Observed 2026-10-08—Source

Migration checks

No linked migration route is available for this model yet.

API versions

Mellum2.1 ThinkingMellum2.1-12B-A2.5B-ThinkingJetBrains/Mellum2.1-12B-A2.5B-Thinkingmellum2-1-12b-thinking