GPT-6 Astra vs MiniMax M3.1 Flash
Vals Science Index?
GPT-6 Astra65.1
MiniMax M3.1 Flash—
| Benchmark | GPT-6 Astra | MiniMax M3.1 Flash |
|---|---|---|
| Humanity's Last Exam | 52.7 | 48 |
| AA Omniscience Index | 42.2 | 15.6 |
| CritPt (physics) | 29.1 | 22.3 |
| AA Intelligence Index 4.3.2 | 49.6 | 42.7 |
| AA Omniscience · Accuracy | 60.6 | 56.2 |
| AA Omniscience · Hallucination Rate | 46.5 | 92.8 |
| AA-LCR (long context) 1.1 | 79.7 | 79.7 |
| GDP.pdf · AA all-pass | 30.4 | 20.8 |
| MLCR-AA | 38.3 | 16.7 |
| Vals Legal Research Bench | 39.4 | 34.1 |
| Arena Text · overall | 1,477 · max | — |
| Arena Text · Chinese | 1,489.3 · max | — |
| Arena Text · English | 1,447.6 · max | — |
| Arena Text · French | 1,424.7 · max | — |
| Arena Text · German | 1,454.7 · max | — |
| Arena Text · instruction following | 1,455.3 · max | — |
| Arena Text · Japanese | 1,403.7 · max | — |
| Arena Text · Korean | 1,427.2 · max | — |
| Arena Text · non-English | 1,432.2 · max | — |
| Arena Text · Polish | 1,427.4 · max | — |
| Arena Text · Russian | 1,441.5 · max | — |
| Arena Text · Spanish | 1,422.5 · max | — |
| SimpleQA Verified v1 | 75.8 | — |
| ARC-AGI-1 · public evaluation | 98.8 | — |
| ARC-AGI-1 · semi-private | 97.5 | — |
| ARC-AGI-2 · public evaluation | 96.7 | — |
| ARC-AGI-2 · semi-private | 92.1 | — |
| ARC-AGI-3 · semi-private | 38.6 | — |
| Chess Puzzles | 74 · max | — |
| FrontierMath Erdos | 2.9 · max | — |
| FrontierMath Tier 4 (v2) | 97.6 | — |
| FrontierMath Tiers 1–3 (v2) | 93.7 · max | — |
| Mystery Game Puzzles | 84 · max | — |
| MathArena · ArXivMath · April 2026 | 90.8 · max | — |
| MathArena · ArXivMath · August 2026 | 88.6 · max | — |
| MathArena · ArXivMath · June 2026 | 94.4 · max | — |
| MathArena · ArXivMath · May 2026 | 95 · max | — |
| MathArena · BrokenArXiv · April 2026 | 97.5 · max | — |
| MathArena · BrokenArXiv · August 2026 | 81.9 · max | — |
| MathArena · BrokenArXiv · June 2026 | 99.1 · max | — |
| MathArena · BrokenArXiv · May 2026 | 91 · max | — |
| MathArena · ArXivLean · June 2026 | 65.2 · max | — |
| MathArena · ArXivLean · September 2026 | 37.7 · max | — |
| Vals MedCode | 48.5 | — |
| Vals MedScribe | 87.9 | — |
| Vals Science Index | 65.1 | — |
Specs
| Spec | GPT-6 Astra | MiniMax M3.1 Flash |
|---|---|---|
| Input, per 1M | $10 | $0.15 |
| Output, per 1M | $50 | $0.60 |
| Cost per task? | $1.54 | $0.22 |
| Speed, tok/s | 59 | 121 |
| Context | 1.05M | 1M |
| Weights | Closed | Closed |
| Released | Sep 2026 | Oct 2026 |
| See images | ✓ | ✓ |
| Read PDFs | Partial | — |
| Hear audio | — | — |
| Watch video | — | ✓ |
| Call tools | ✓ | ✓ |
| Force a tool call | Partial | ? |
| Return strict JSON | ✓ | — |
| Search the web | ✓ | ? |
| Run code | ✓ | ? |
| Use a computer | ✓ | ? |
What breaks when you switch
GPT-6 Astra → MiniMax M3.1 Flash
Context: 1.05M → 1M
No strict JSON
Complete model response must be appended›
In multi-turn tools, preserve the complete assistant response, including reasoning_content and tool_calls, to maintain reasoning continuity.
MiniMax M3.1 Flash → GPT-6 Astra
Monitoring can return HTTP 403›
Misalignment monitoring can return HTTP 403 before streaming or errors after output; match misalignment_policy_violation and handle stream errors.
No none reasoning effort›
The none reasoning effort is unsupported on GPT-6 Astra and GPT-6.1 Sol; use low instead.
Remove unsupported sampling parameters›
When reasoning effort is not none, remove temperature, top_p and top_logprobs, plus Chat Completions logprobs or Responses output logprobs inclusion.