SpaceX AI
SpaceX AI models with results here, each shown on its own board.
- Models
- 10
- Results
- 36
- Boards
- 12 of 14
Models
| Model | Kind | Released | Boards |
|---|---|---|---|
| Grok 4.7 | Model | 21 Sep 2026 | 7 |
| Grok 4.6 | Model | 12 Aug 2026 | 6 |
| Grok 4.5 | Model | 8 Jul 2026 | 2 |
| Grok 4.20 | Model | 10 Mar 2026 | 4 |
| Grok 4.1 Fast (Reasoning) | Model | 19 Nov 2025 | 2 |
| Grok 4.1 Fast Non-Reasoning | Model | 19 Nov 2025 | 2 |
| Grok 4 Fast (Non-Reasoning) | Model | 19 Sep 2025 | 2 |
| Grok 4 Fast (Reasoning) | Model | 19 Sep 2025 | 2 |
| Grok 4 | Model | 9 Jul 2025 | 2 |
| Grok 4.3 | Model | Not stated | 4 |
Results
One line per result. Tall tick: the board leader.
Clinical reasoning and knowledge
- 0.567Rank 22 of 43Leader GPT-6 Astra (Anthropic run) 0.703
- 0.485Rank 34 of 43Leader GPT-6 Astra (Anthropic run) 0.703
- MedXpertQA (MM)Meta's Muse Spark launch table (Meta reports the better of vendor self-reports and its own reproduction)65.8Rank 13 of 22 here, 5 models on the boardLeader GPT-5.6 Sol 81.5
- 53.7Rank 8 of 8 here, 11 models on the boardLeader GPT-5.6 Sol 60.2
- 83.3Rank 13 of 15 here, 16 models on the boardLeader Claude Opus 5 94.6
- 59.38Rank 9 of 12Leader Claude Opus 5.5 73.04
- 59.16Rank 10 of 12Leader Claude Opus 5.5 73.04
Documentation and coding
- MedScribe (Vals AI)model ID grok/grok-4.7; temperature=1; top_p=0.95; reasoning_effort=xhigh89.38Rank 6 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
- MedScribe (Vals AI)model ID grok/grok-4.5; temperature=1; top_p=0.95; max_output_tokens=30000; reasoning_effort=high86.88Rank 17 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
- 86.53Rank 20 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
- MedScribe (Vals AI)model ID grok/grok-4-fast-reasoning; temperature=1; top_p=0.95; max_output_tokens=3000081.63Rank 51 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
- MedScribe (Vals AI)model ID grok/grok-4-fast-non-reasoning; temperature=1; top_p=0.95; max_output_tokens=3000079.72Rank 58 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
- MedScribe (Vals AI)model ID grok/grok-4-1-fast-reasoning; temperature=1; top_p=0.95; max_output_tokens=3000078.73Rank 61 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
- MedScribe (Vals AI)model ID grok/grok-4-0709; temperature=1; top_p=0.95; max_output_tokens=3000078.15Rank 63 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
- MedScribe (Vals AI)model ID grok/grok-4-1-fast-non-reasoning; temperature=1; top_p=0.95; max_output_tokens=3000077.46Rank 67 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
- MedScribe (Vals AI)model ID grok/grok-4.3; temperature=1; top_p=0.95; max_output_tokens=3000074.40Rank 79 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
- MedScribe (Vals AI)model ID grok/grok-4.20-0309-reasoning; temperature=1; top_p=0.95; max_output_tokens=3000063.41Rank 100 of 106 here, 105 models on the boardLeader Claude Opus 5.5 91.43
- 49.55Rank 20 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
- MedCode (Vals AI)model ID grok/grok-4.6; reasoning_effort=high; temperature=1; top_p=0.95; max_output_tokens=3000044.71Rank 38 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
- MedCode (Vals AI)model ID grok/grok-4.5; reasoning_effort=high; temperature=1; top_p=0.95; max_output_tokens=3000043.29Rank 44 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
- MedCode (Vals AI)model ID grok/grok-4-0709; temperature=1; top_p=0.95; max_output_tokens=3000038.08Rank 70 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
- 38.07Rank 71 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
- MedCode (Vals AI)model ID grok/grok-4-fast-reasoning; temperature=1; top_p=0.95; max_output_tokens=3000037.38Rank 73 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
- MedCode (Vals AI)model ID grok/grok-4.20-0309-reasoning; temperature=1; top_p=0.95; max_output_tokens=3000032.16Rank 88 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
- MedCode (Vals AI)model ID grok/grok-4-fast-non-reasoning; temperature=1; top_p=0.95; max_output_tokens=3000030.04Rank 94 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
- MedCode (Vals AI)model ID grok/grok-4-1-fast-non-reasoning; temperature=1; top_p=0.95; max_output_tokens=3000028.35Rank 97 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
- MedCode (Vals AI)model ID grok/grok-4-1-fast-reasoning; temperature=1; top_p=0.95; max_output_tokens=3000028.08Rank 98 of 104 here, 103 models on the boardLeader Claude Opus 5 63.57
- 20.0Rank 15 of 27Leader Claude Sonnet 5.5 (Max, Default Fallback) 41.7
EHR and workflow agents
- 5.3Rank 27 of 28 here, 12 models on the boardLeader Claude Opus 5.5 (max) 68.4
- 5.8Rank 37 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
- 4.4Rank 39 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
- 2.2Rank 41 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
- 0.4Rank 42 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
- 88.16Rank 12 of 20Leader Claude Opus 5 92.68
- 27.6Rank 6 of 15Leader Claude Opus 5.5 48.3
- 14.8Rank 11 of 15Leader Claude Opus 5.5 48.3