THE SCOREBOARD FOR WHAT'S NEXTAI + QUANTUM, SCORED. COMPARED. EXPLAINED.
AIQUANTUMSCORE.

EVIDENCE COVERAGE

What has been
tested together?

16 of 41 models qualify for an overall Quantum Score. Category scores require current independent evidence in a compatible cohort of at least three models. REVAL testing and measured Speed are tracked separately.

ModelcodingreasoningmathagentsmultimodalREVAL™SpeedOverall
GPT-6 Astra7494876097Not testedMeasured74
GPT-6 Sol4767792062Not testedNot measured52
GPT-6 Luna33397522No dataNot testedMeasured41
GPT-6.1 Sol8883No data8548Not testedMeasured
Not qualified

Qualified category evidence: coding, reasoning, agents, multimodal. An overall score is withheld because only 7 independent observations (minimum 8). Evidence still missing or lacking comparable overlap: math, research, speed.

GPT-5.6 Sol7569542044Not testedNot measured52
GPT-5.6 Terra49678034No dataNot testedMeasured54
GPT-5.6 Luna61516720No dataNot testedNot measured51
Claude Fable 5.17086997052Not testedNot measured68
Claude Opus 5.59491929698Not testedMeasured88
Claude Sonnet 5.595918478PartialNot testedNot measured84
Claude Haiku 4.5No dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

Gemini 3.8 Flash3261953091Not testedNot measured57
Gemini 3.7 Flash4791812083Not testedNot measured62
Gemini 3.6 Flash47797520No dataNot testedMeasured
Not qualified

Qualified category evidence: coding, reasoning, math, agents. An overall score is withheld because only 2 benchmark source domains (minimum 3). Evidence still missing or lacking comparable overlap: research, multimodal, speed.

Gemini 3.5 Flash3275812080Not testedNot measured53
Gemini 3.5 Flash-Lite34000No dataNot testedMeasured
Not qualified

Qualified category evidence: coding, reasoning, math, agents. An overall score is withheld because only 1 benchmark source domains (minimum 3); only 7 independent observations (minimum 8); only 1 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: research, multimodal, speed.

Gemini 3.1 Pro Preview198182071Not testedNot measured46
Grok 4.64667663950Not testedNot measured51
Grok 4.51990823222Not testedNot measured45
DeepSeek V4.1 Flash4692691000Not testedNot measured60
DeepSeek V4 Pro33957940No dataNot testedNot measured
Not qualified

Qualified category evidence: coding, reasoning, math, agents. An overall score is withheld because only 2 benchmark source domains (minimum 3). Evidence still missing or lacking comparable overlap: research, multimodal, speed.

Mistral Medium 3.5No dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

Mistral Small 4No dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

Mistral Large 3No dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

Llama 4 ScoutNo dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

Llama 4 MaverickNo dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

Qwen3.5-397B-A17BNo dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

Qwen3.5-122B-A10BNo dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

gpt-4.1No dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

gpt-4.1-miniNo dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

gpt-4.1-nanoNo dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

gpt-5No dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

gpt-5-miniNo dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

gpt-5-nanoNo dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

gpt-5.1No dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

gpt-5.2No dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

gpt-5.4-miniNo dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

gpt-5.4-nanoNo dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

Gemini 4 Argon48100No data73No dataNot testedNot measured
Not qualified

Qualified category evidence: coding, reasoning, agents. An overall score is withheld because only 2 benchmark source domains (minimum 3); only 7 independent observations (minimum 8); only 49% of the required weighted category coverage; only 3 qualified categories (minimum 4). Evidence still missing or lacking comparable overlap: math, research, multimodal, speed.

Muse WonderPartialPartialNo dataPartialNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 1 benchmark source domains (minimum 3); only 4 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 1 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

Muse Wonder FullNo dataNo dataNo dataNo dataNo dataNot testedNot measured
Not qualified

An overall score is withheld because only 0 benchmark source domains (minimum 3); only 0 independent observations (minimum 8); only 0% of the required weighted category coverage; only 0 qualified categories (minimum 4); only 0 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: coding, reasoning, math, research, agents, multimodal, speed.

How scores qualify →