The Open-Weight League
The weekly form guide to open-weight models worth running on your own infrastructure.
INT Intelligence · COD Coding · SPD Speed t/s · OPEN Openness / 18 · PTS Blend 40·25·15·20
Season 2026/27 · Matchday 01| # | Club | Nation | INTIntelligence Index · reasoning, knowledge & agentic ability · AA Index v4.1 | CODCoding Index · software engineering & code generation benchmarks | SPDOutput Speed · median generation throughput, tokens per second | OPENOpenness Index · weights & transparency, scored out of 18 | PTSLeague Points · blended score · INT 40 · COD 25 · SPD 15 · OPEN 20 |
|---|---|---|---|---|---|---|---|
| 1 | Kimi K3Moonshot AI | CHN | 57 | 56 | 68 | 14 | –96 |
| 2 | GLM-5.2Z.AI · Zhipu AI | CHN | 55 | 54 | 94 | 16 | –93 |
| 3 | Kimi K2.6Moonshot AI | CHN | 54 | 54 | 80 | 14 | –91 |
| 4 | MiMo V2.5 ProXiaomi | CHN | 54 | 50 | 84 | 12 | –89 |
| 5 | DeepSeek V4 ProDeepSeek | CHN | 52 | 52 | 62 | 15 | –87 |
| 6 | Muse Spark 1.1Meta | USA | 51 | 47 | 76 | 12 | –84 |
| 7 | MiniMax M3MiniMax | CHN | 50 | 49 | 86 | 13 | –82 |
| 8 | DeepSeek V4 FlashDeepSeek | CHN | 46 | 45 | 130 | 15 | –79 |
| 9 | Llama 5Meta | USA | 44 | 41 | 60 | 13 | –76 |
| 10 | InklingThinking Machines | USA | 41 | 40 | 72 | 13 | –73 |
| 11 | GLM-5.1Z.AI · Zhipu AI | CHN | 39 | 40 | 90 | 16 | –70 |
| 12 | Nemotron 3 UltraNVIDIA | USA | 38 | 35 | 70 | 15 | –67 |
| 13 | MiniMax M2.7MiniMax | CHN | 35 | 36 | 82 | 12 | –64 |
| 14 | Qwen3.5 72BAlibaba | CHN | 31 | 30 | 84 | 13 | –60 |
| 15 | Gemma 4 31BGoogle | USA | 29 | 30 | 98 | 10 | –57 |
| 16 | Mistral Large 3Mistral AI | FRA | 29 | 28 | 76 | 11 | –55 |
| 17 | K2K2 ThinkMBZUAI · IFM | ARE | 26 | 24 | 70 | 14 | –52 |
| 18 | gpt-oss-120bOpenAI | USA | 24 | 23 | 112 | 11 | –49 |
| 19 | Solar Pro 3Upstage | KOR | 24 | 22 | 78 | 11 | –46 |
| 20 | Phi-5Microsoft | USA | 21 | 20 | 102 | 10 | –43 |
Key — what the columns mean
INT
Intelligence Index. Reasoning, knowledge & agentic ability · AA Index v4.1
COD
Coding Index. Software engineering & code generation benchmarks
SPD
Output Speed. Median generation throughput · tokens per second
OPEN
Openness Index. Weights & transparency, scored out of 18
PTS
League Points. Blended score · INT 40 · COD 25 · SPD 15 · OPEN 20
Methodology
Every underlying score on this table comes from Artificial Analysis, an independent AI benchmarking organisation. We do not run our own evaluations and we do not adjust theirs.
INT is the Artificial Analysis Intelligence Index (v4.1): reasoning, knowledge and agentic ability. COD is their Coding Index across software-engineering and code-generation benchmarks. SPD is median output speed in tokens per second. OPEN is their Openness Index — weights availability, licence and transparency — scored out of 18.
PTS is the only number we compute: each index is normalised to 0–100, then blended INT 40% · COD 25% · SPD 15% · OPEN 20%. The weights are stated here precisely so the table can be checked, argued with, or rebuilt by anyone.
Valarian builds no models and holds no stake in any lab on this table. ACRA runs whichever club you pick — so we have no reason to favour one. The table exists because our customers keep asking the same question: which open-weight models are actually good now?
Valarie’s squad
Match-fit today: validated in Valarie, uploaded privately into ACRA, and served from infrastructure you control.
DeepSeek V4 Pro
DeepSeek · CHN
live in ACRADeploy your stack
Llama 5
Meta · USA
live in ACRADeploy your stack
Qwen3.5 72B
Alibaba · CHN
live in ACRADeploy your stack
Gemma 4 31B
Google · USA
live in ACRADeploy your stack
Mistral Large 3
Mistral AI · FRA
live in ACRADeploy your stack
gpt-oss-120b
OpenAI · USA
live in ACRADeploy your stack
Any open-weight club is loadable · Control Plane → Private AI → upload
