The LLM benchmark aggregator.

OpenBMB 1B

OpenBMB · 1B

§ 1 · Profile

What it is good at

Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.

Agents44.7−23.4—/267✱0/5

Tool use36.5−37.5—/81✱0/1

Reasoning48.6−18.3—/178✱0/4

Mathematics50.2−15.5—/140✱0/2

Science31.6−31.9—/122✱0/1

Coding50.9−18.2—/164✱0/5

Code generation52.2−17.8—/77✱0/2

§ 2 · Head to head

What it beats, and what beats it

The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for OpenBMB 1B, left for the other.

Claude 3.5 Haikuwon 5 · lost 0

GPT-4o Miniwon 6 · lost 0

Qwen3.5 0.8Bwon 6 · lost 1

DeepSeek V3won 5 · lost 1

GPT-4owon 4 · lost 1

Claude 3.5 Sonnetwon 4 · lost 1

Llama 4 Scout Instructwon 4 · lost 1

Mistral Large 3won 4 · lost 1

Mistral Medium 3.5won 4 · lost 1

Qwen3.6 27Bwon 4 · lost 1

Nemotron 3 Ultra 550B A55Bwon 4 · lost 1

Kimi K2.7 Codewon 4 · lost 1

Grok Build 0.1won 4 · lost 1

NVIDIA Nemotron 3 Nano 4Bwon 5 · lost 2

Nemotron 3 Ultrawon 4 · lost 2

GPT-4.1 Nanowon 4 · lost 2

Llama 4 Maverick Instructwon 4 · lost 2

Gemini 3.5 Flash Litewon 4 · lost 2

Grok 4.3won 4 · lost 2

GPT-5.4 Miniwon 4 · lost 2

Qwen3.6 Pluswon 4 · lost 2

Command Awon 4 · lost 2

Claude Opus 4won 3 · lost 2

Gemma 4 E4Bwon 3 · lost 2

Mistral Largewon 3 · lost 2

Inkling Smallwon 3 · lost 2

Mimo V2.5won 3 · lost 2

Mimo V2.5 Prowon 3 · lost 2

DeepSeek V4 Flash Visionwon 3 · lost 2

Qwen3.8 Flash Nextwon 3 · lost 2

G9v3 3Bwon 4 · lost 3

Inklingwon 4 · lost 3

MiniMax M3won 4 · lost 3

Granite 4.2 8Bwon 3 · lost 3

Granite 4.2 30Bwon 3 · lost 3

GPT-4.1 Miniwon 3 · lost 3

G9v3 39A5Bwon 3 · lost 3

Gemini 3.5 Flashwon 3 · lost 3

Qwen3.7 Maxwon 3 · lost 3

Grok 4.5won 3 · lost 3

Gemini 3.6 Flashwon 3 · lost 3

Kimi K2.6won 3 · lost 3

Granite 4.2 3Bwon 3 · lost 4

Qwen3.8 27Bwon 3 · lost 4

DeepSeek R1won 2 · lost 3

Gemini 3.1 Flash Litewon 2 · lost 3

Gemma 4 12Bwon 2 · lost 3

Claude 3.7 Sonnetwon 2 · lost 3

GPT OSS 120Bwon 2 · lost 3

Gemini 2.5 Flash Litewon 2 · lost 3

Mistral Smallwon 2 · lost 3

Muse Spark 1.2won 2 · lost 3

O3 Miniwon 2 · lost 4

Gemini 2.5 Prowon 2 · lost 4

Gemma 4 31Bwon 2 · lost 4

Qwen3.5 9Bwon 2 · lost 4

Gemini 3.1 Prowon 2 · lost 4

Nemotron 3 Superwon 2 · lost 4

Claude Sonnet 4won 2 · lost 4

Qwen3.6 35B A3Bwon 2 · lost 4

GPT-5.4 Nanowon 2 · lost 4

K2 Horizon 32Bwon 2 · lost 4

K2 Horizon 7Bwon 2 · lost 4

GPT-4.1won 2 · lost 4

Kimi K2won 2 · lost 4

Muse Spark 1.1won 2 · lost 4

DeepSeek V4 Flashwon 2 · lost 4

GLM-5.3 Flashwon 2 · lost 4

Qwen3.5 2Bwon 2 · lost 5

Qwen3.5 4Bwon 2 · lost 5

K2 Horizon 3.7Bwon 2 · lost 5

GPT-5.2won 2 · lost 5

Gemini 2.5 Flashwon 2 · lost 5

Claude Opus 4.6won 1 · lost 4

Muse Sparkwon 1 · lost 4

MiniMax M2.7won 1 · lost 4

GPT-5.1won 1 · lost 4

GLM-4.7won 1 · lost 4

GLM-5.1won 1 · lost 4

Kimi K2.5won 1 · lost 4

GPT-5 Nanowon 1 · lost 4

Grok 4.7won 1 · lost 4

GPT-5 Miniwon 1 · lost 5

Claude Haiku 4.5won 1 · lost 5

DeepSeek V3.2won 1 · lost 5

GPT-5.4won 1 · lost 5

K2 Horizon MoVA 36B A4Bwon 1 · lost 5

Claude Sonnet 4.5won 1 · lost 5

Gemini 3.8 Flashwon 1 · lost 5

GLM-4.6won 1 · lost 5

DeepSeek V4 Prowon 1 · lost 5

Grok 4.1 Fastwon 1 · lost 5

Gemini 3 Prowon 1 · lost 5

GLM-5.3won 1 · lost 5

Grok 4.6won 1 · lost 5

Qwen3.8 Maxwon 1 · lost 5

K2 Horizon 0.9Bwon 1 · lost 6

Qwen3 235B A22B Instructwon 1 · lost 6

O4 Miniwon 1 · lost 6

GPT-5.6 Terrawon 1 · lost 6

GPT-5.6 Lunawon 1 · lost 6

Claude Opus 4.5won 1 · lost 6

Grok 3 Miniwon 0 · lost 5

GPT-5won 0 · lost 5

GPT-6 Lunawon 0 · lost 5

GPT-6 Solwon 0 · lost 5

GPT-6 Astrawon 0 · lost 5

Muse Spark 1.3won 0 · lost 5

Claude Opus 5.5won 0 · lost 5

Muse Glimmer-30Bwon 0 · lost 6

Gemini 3.7 Flashwon 0 · lost 6

GPT-5.5won 0 · lost 6

Claude Sonnet 4.6won 0 · lost 6

Claude Opus 4.7won 0 · lost 6

K2 Horizon 375B A23Bwon 0 · lost 6

Grok 4won 0 · lost 6

Claude Opus 4.8won 0 · lost 6

DeepSeek V4.1 Flashwon 0 · lost 6

GPT-5.6 Solwon 0 · lost 6

Kimi K3won 0 · lost 6

Claude Fable 5.1won 0 · lost 6

Claude Fable 5won 0 · lost 6

Claude Opus 5won 0 · lost 6

O3won 0 · lost 7

GLM-5.2won 0 · lost 7

Claude Sonnet 5won 0 · lost 7

§ 3 · Sources

Where the numbers come from

1 publication, 8 figures. Every one links to the page it was read from.

✱✱ IFM — K2 Horizon launch ↗the model’s own publisher8 measuresread 2026-09-27

GPQA Diamond 26.3%HMMT Feb 2026 23.3%BFCL v4 25.2%HumanEval+ 65.2%MBPP+ 60.6%AIME 2025 40.4%AIME 2026 40.4%LiveCodeBench v6 33.5%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=openbmb-1b)](https://publicai.io/model-index/m/openbmb-1b)