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.
| Model | coding | reasoning | math | agents | multimodal | REVAL™ | Speed | Overall |
|---|---|---|---|---|---|---|---|---|
| GPT-6 Astra | 74 | 94 | 87 | 60 | 97 | Not tested | Measured | 74 |
| GPT-6 Sol | 47 | 67 | 79 | 20 | 62 | Not tested | Not measured | 52 |
| GPT-6 Luna | 33 | 39 | 75 | 22 | No data | Not tested | Measured | 41 |
| GPT-6.1 Sol | 88 | 83 | No data | 85 | 48 | Not tested | Measured | Not qualifiedQualified 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 Sol | 75 | 69 | 54 | 20 | 44 | Not tested | Not measured | 52 |
| GPT-5.6 Terra | 49 | 67 | 80 | 34 | No data | Not tested | Measured | 54 |
| GPT-5.6 Luna | 61 | 51 | 67 | 20 | No data | Not tested | Not measured | 51 |
| Claude Fable 5.1 | 70 | 86 | 99 | 70 | 52 | Not tested | Not measured | 68 |
| Claude Opus 5.5 | 94 | 91 | 92 | 96 | 98 | Not tested | Measured | 88 |
| Claude Sonnet 5.5 | 95 | 91 | 84 | 78 | Partial | Not tested | Not measured | 84 |
| Claude Haiku 4.5 | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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 Flash | 32 | 61 | 95 | 30 | 91 | Not tested | Not measured | 57 |
| Gemini 3.7 Flash | 47 | 91 | 81 | 20 | 83 | Not tested | Not measured | 62 |
| Gemini 3.6 Flash | 47 | 79 | 75 | 20 | No data | Not tested | Measured | Not qualifiedQualified 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 Flash | 32 | 75 | 81 | 20 | 80 | Not tested | Not measured | 53 |
| Gemini 3.5 Flash-Lite | 34 | 0 | 0 | 0 | No data | Not tested | Measured | Not qualifiedQualified 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 Preview | 19 | 81 | 82 | 0 | 71 | Not tested | Not measured | 46 |
| Grok 4.6 | 46 | 67 | 66 | 39 | 50 | Not tested | Not measured | 51 |
| Grok 4.5 | 19 | 90 | 82 | 32 | 22 | Not tested | Not measured | 45 |
| DeepSeek V4.1 Flash | 46 | 92 | 69 | 100 | 0 | Not tested | Not measured | 60 |
| DeepSeek V4 Pro | 33 | 95 | 79 | 40 | No data | Not tested | Not measured | Not qualifiedQualified 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 3.5 | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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 4 | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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 3 | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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 Scout | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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 Maverick | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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-A17B | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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-A10B | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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 | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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-mini | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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-nano | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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 | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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-mini | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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-nano | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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-5.1 | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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-5.2 | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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-mini | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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-nano | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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 Argon | 48 | 100 | No data | 73 | No data | Not tested | Not measured | Not qualifiedQualified 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 Wonder | Partial | Partial | No data | Partial | No data | Not tested | Not measured | Not qualifiedAn 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 Full | No data | No data | No data | No data | No data | Not tested | Not measured | Not qualifiedAn 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. |