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

THE LEADERBOARD

Numbers on
the board.

Overall and category scores are grounded in current, comparable records. Seven-day change needs daily snapshots.

#ModelQuantum ScoreCodingReasoningREVAL™
ⓘREVAL™ Research Evaluation Index — our proprietary 0–100 benchmark measuring real-world AI research performance. Methodology →
AgentsSpeedValue
01Claude Opus 5.5Anthropic889491Not tested9690 tok/sMax · 2026-10-0152
02Claude Sonnet 5.5Anthropic849591Not tested78Not measured62
03GPT-6 AstraOpenAI747494Not tested6052 tok/sMax · 2026-10-0127
04Claude Fable 5.1Anthropic687086Not tested70Not measured25
05Gemini 3.7 FlashGoogle624791Not tested20Not measured56
06DeepSeek V4.1 FlashDeepSeek604692Not tested100Not measured58
07Gemini 3.8 FlashGoogle573261Not tested30Not measured54
08GPT-5.6 TerraOpenAI544967Not tested3493.6 tok/sMax · 2026-10-0140
09Gemini 3.5 FlashGoogle533275Not tested20Not measured43
10GPT-6 SolOpenAI524767Not tested20Not measured39
11GPT-5.6 SolOpenAI527569Not tested20Not measured29
12GPT-5.6 LunaOpenAI516151Not tested20Not measured48
13Grok 4.6xAI514667Not tested39Not measured41
14Gemini 3.1 Pro PreviewGoogle461981Not tested0Not measured35
15Grok 4.5xAI451990Not tested32Not measured38
16GPT-6 LunaOpenAI413339Not tested22122.4 tok/sMax · 2026-10-0141
17GPT-6.1 SolOpenAI
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.

See evidence →
8883Not tested8564 tok/sMax · 2026-10-0154
18Claude Haiku 4.5Anthropic
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
19Gemini 3.6 FlashGoogle
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.

See evidence →
4779Not tested20176.6 tok/sHigh · 2026-10-0148
20Gemini 3.5 Flash-LiteGoogle
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.

See evidence →
340Not tested0354.5 tok/sProvider default (not specified by source) · 2026-10-018
21DeepSeek V4 ProDeepSeek
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.

See evidence →
3395Not tested40Not measured52
22Mistral Medium 3.5Mistral
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
23Mistral Small 4Mistral
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
24Mistral Large 3Mistral
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
25Llama 4 ScoutMeta
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
26Llama 4 MaverickMeta
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
27Qwen3.5-397B-A17BQwen / Alibaba
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
28Qwen3.5-122B-A10BQwen / Alibaba
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
29gpt-4.1OpenAI
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
30gpt-4.1-miniOpenAI
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
31gpt-4.1-nanoOpenAI
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
32gpt-5OpenAI
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
33gpt-5-miniOpenAI
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
34gpt-5-nanoOpenAI
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
35gpt-5.1OpenAI
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
36gpt-5.2OpenAI
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
37gpt-5.4-miniOpenAI
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
38gpt-5.4-nanoOpenAI
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
39Gemini 4 ArgonGoogle
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.

See evidence →
48100Not tested73Not measuredNo data
40Muse WonderMeta
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data
41Muse Wonder FullMeta
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.

See evidence →
No dataNo dataNot testedNo dataNot measuredNo data