Skip to main content
BenchLM
Data

Data as of November 21, 2026 · How the score is built

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

CurrentOpen WeightReasoning

Decision readingMellum2.1-12B-A2.5B-Thinking is tracked, but not publicly ranked yet. The profile exposes 7 sourced benchmark rows and leaves unsupported fields blank until a published record exists.

Email me when its price, rank or availability changes.

Capability

Unranked

field median 47.5Not eligible for a public rank

Price

Self-hosted; infrastructure cost varies

input median $0.60No comparable first-party hosted token rate

Speed

Not measured

field median 93.5 tok/sTime to first token not measured

Context

131072 tokenstokens

field median 256,000Maximum output length is tracked separately

Decision snapshot

How much published evidence this model has, where that evidence is strongest, and what to validate before choosing it. It has no public rank, so no field position is shown.

Strongest published evidence

Published rows are visible, but no category has enough eligible evidence for a comparative rank.

Validate before choosing

7 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.

Source-linked · 7 displayable benchmark rows

Category score record

Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticWeight 22%1 benchmarkVerified
Score pending
CodingRank Not rankedWeight 20%3 benchmarksVerified
21.1
ReasoningWeight 17%0 benchmarksNot measured
Not measured
MultimodalWeight 12%0 benchmarksNot measured
Not measured
KnowledgeWeight 12%2 benchmarksVerified
Score pending
MultilingualWeight 7%0 benchmarksNot measured
Not measured
Inst. FollowingWeight 5%1 benchmarkVerified
Score pending
MathWeight 5%0 benchmarksNot measured
Not measured

7 of 952 tracked benchmark slots have displayable evidence · bars run 0–100

Coverage details

How much of this is verified

Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.

  1. Agentic1/1 verified
  2. Coding3/3 verified
  3. ReasoningNot measured
  4. MultimodalNot measured
  5. Knowledge2/2 verified
  6. MultilingualNot measured
  7. Inst. Following1/1 verified
  8. MathNot measured
Verified sourceProvisionalNot measured

Benchmark ledger

Every result says who ran the test. For this model, JetBrains ran all 17. Coding opens by default. The tick marks the best source-verified result in the catalog; provisional leaders do not set the reference.

Overall rank
Not ranked yet
No benchmark-run or independent results yet
Reported by JetBrains
17
Shown with that label
Run by a benchmark
0
None yet
Independent runs
0
None yet
Coding3 rows
Coding benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
LiveCodeBench v682.0%

Best verified: Sakana Fugu-Ultra · 93.2%

Gap11.2 behindReported by JetBrainsWeighted benchmark5% ref. weight
SWE-bench Pro28%

Best verified: Claude Fable 5.2 · 93%

Gap65 behindReported by JetBrainsWeighted benchmark4% ref. weight
SWE-bench VerifiedSoftware Engineering Benchmark Verified47%

Best verified: Claude Opus 5 · 96%

Gap49 behindReported by JetBrainsShown only
Agentic1 row
Agentic benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
Terminal-Bench 2.117.4%

Best verified: SWE-2 · 92.8%

Gap75.4 behindReported by JetBrainsWeighted benchmark2% ref. weight
Knowledge2 rows
Knowledge benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
GPQA-DGPQA Diamond64.6%

Best verified: GPT-6.2 Astra · 97.0%

Gap32.4 behindReported by JetBrainsWeighted benchmark3% ref. weight
MMLU-Redux87.8%

Best verified: Qwen3.7 Max · 95%

Gap7.2 behindReported by JetBrainsWeighted benchmark1% ref. weight
Inst. Following1 row
Inst. Following benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
IFEvalInstruction-Following Eval90.6%

Best verified: LFM2.5-24B-A2B · 96.8%

Gap6.2 behindReported by JetBrainsShown only
Other lab-reported results10 rowsAnother metric, split or setting, or a test without a page
Results the lab reported, with the metric and setup, who ran each test, and that none counts toward a rank
HumanEval+Score · Thinking mode, greedy decoding; JetBrains ran every model in the table with the same pipeline; HumanEval+ (EvalPlus) adds tests to the HumanEval problems, the board stores base HumanEval91.5%Reported by JetBrainsShown only
XSTestScore · Thinking mode, greedy decoding; JetBrains ran every model in the table with the same pipeline88.8%Reported by JetBrainsShown only
GSM-PlusScore · Thinking mode, greedy decoding; JetBrains ran every model in the table with the same pipeline88.3%Reported by JetBrainsShown only
AIME 2025/2026 (mean)Mean of AIME 2025 and AIME 2026 (30 questions each) · Thinking mode, greedy decoding; JetBrains ran every model in the table with the same pipeline; a combined result, not a single-year score83.3%Reported by JetBrainsShown only
MBPP+Score · Thinking mode, greedy decoding; JetBrains ran every model in the table with the same pipeline79.4%Reported by JetBrainsShown only
BFCL v4Macro-average of five subtasks (v1, v2, v3, web search, memory) · Thinking mode, greedy decoding; JetBrains ran every model in the table with the same pipeline; not the official BFCL v4 overall weighting62.3%Reported by JetBrainsShown only
ToolHopScore · Thinking mode, greedy decoding; JetBrains ran every model in the table with the same pipeline49.1%Reported by JetBrainsShown only
MixEval-HardScore · Thinking mode, greedy decoding; JetBrains ran every model in the table with the same pipeline46.4%Reported by JetBrainsShown only
WorkBenchScore · Thinking mode, greedy decoding; JetBrains ran every model in the table with the same pipeline44.6%Reported by JetBrainsShown only
HarmBenchHarmful rate (lower is better) · Thinking mode, greedy decoding; JetBrains ran every model in the table with the same pipeline8.5%Reported by JetBrainsShown only

Outlined bars are lab-reported. Filled bars are benchmark-run or independent. Bars run 0–100; the dark tick marks the best source-verified value.

Lineage

The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.

  1. May 28, 2026

    Mellum2-12B-A2.5B-Thinking

    Not publicly ranked · Price not listed

  2. Oct 8, 2026 · you are here

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

    Not publicly ranked · Price not listed

Thinking

Spec sheet

Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.

Weights model ID
JetBrains/Mellum2.1-12B-A2.5B-ThinkingJetBrains Mellum2.1 Thinking model card
Context window
131072 tokensJetBrains Mellum2.1 Thinking config
Maximum output
Not sourced yet
Knowledge cutoff
Not sourced yet
Parameters
12B total · 2.5B active · MOE
Availability
Hugging Face · Self-hosted vLLM · GGUF: llama.cpp, Ollama, LM StudioJetBrains Mellum2.1 Thinking GGUF model card
Cloud regions
Not tracked yet
API capabilities
Tool calling, structured outputs, and batch support are not tracked yet
Prompt caching
Not documented in the pricing recordJetBrains Mellum2.1 Thinking model card
Self-host
Mellum2.1-12B-A2.5B-Thinking needs ~24GB VRAM (1× NVIDIA RTX 4090 (24GB)).
Rate limits
Not tracked yet

How to read this profile

The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.

We track Mellum2.1-12B-A2.5B-Thinking, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.

Mellum2.1-12B-A2.5B-Thinking is a open weight model with a 131072 tokens context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.

Apache 2.0 weights on Hugging Face, with vLLM serving instructions. Official GGUF builds support llama.cpp, Ollama, and LM Studio. No first-party hosted API token rate is published.

JetBrains released Mellum2.1 Thinking on October 8, 2026 under Apache 2.0. The MoE has 12B total parameters, 2.5B active, and a 131,072-token context confirmed by config.json. All stored scores are self-reported by JetBrains in thinking mode. Non-agentic tests use greedy decoding. SWE-bench Verified, SWE-bench Pro, and Terminal-Bench 2.1 use Pi v0.73.1 with shell and file tools, temperature 1.0, a 114K-token context, and up to 16K tokens per turn. LiveCodeBench v6 and Terminal-Bench 2.1 remain separate from other versions. JetBrains' unmapped results on BFCL v4 (a macro-average of v1, v2, v3, web search, and memory subtasks), HumanEval+, MBPP+, AIME 2025/2026 (mean), GSM-Plus, WorkBench, ToolHop, MixEval-Hard, XSTest, and HarmBench (harmful rate, lower is better) are listed in the benchmark ledger. The combined AIME result is not an individual-year score. GGUF builds are quantizations of this model, without separate task-benchmark results.

Its explicit predecessor is Mellum2-12B-A2.5B-Thinking. 7 of 952 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.

Last updated November 21, 2026. Runtime fields remain blank until a sourced snapshot exists.

Deployment options

Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Mellum2.1-12B-A2.5B-Thinking
API / moNo API price on file
Self-host / mo$298
Break-even—
Model the full break-even

Questions

How does Mellum2.1-12B-A2.5B-Thinking perform overall in AI benchmarks?

Mellum2.1-12B-A2.5B-Thinking has 7 source-displayable benchmark rows, but it does not qualify for a public overall rank. The available rows remain visible by category without being converted into a site-wide score. Missing evidence stays blank instead of being estimated from an earlier model.

Is Mellum2.1-12B-A2.5B-Thinking good for knowledge and understanding?

Mellum2.1-12B-A2.5B-Thinking has source-displayable benchmark coverage for knowledge and understanding, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is Mellum2.1-12B-A2.5B-Thinking good for coding and programming?

Mellum2.1-12B-A2.5B-Thinking has source-displayable benchmark coverage for coding and programming, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is Mellum2.1-12B-A2.5B-Thinking good for agentic tool use and computer tasks?

Mellum2.1-12B-A2.5B-Thinking has source-displayable benchmark coverage for agentic tool use and computer tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is Mellum2.1-12B-A2.5B-Thinking good for instruction following?

Mellum2.1-12B-A2.5B-Thinking has source-displayable benchmark coverage for instruction following, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is Mellum2.1-12B-A2.5B-Thinking open source?

Mellum2.1-12B-A2.5B-Thinking is an open-weight model from JetBrains. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.

Does Mellum2.1-12B-A2.5B-Thinking have full benchmark coverage on BenchLM?

No. Mellum2.1-12B-A2.5B-Thinking currently has 7 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.

What is the context window size of Mellum2.1-12B-A2.5B-Thinking?

Mellum2.1-12B-A2.5B-Thinking has a documented context window of 131072 tokens. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.

Compare Mellum2.1-12B-A2.5B-Thinking with every tracked model1034 comparisons