# AI Co-Mathematician vs Grok 4.6

> Grok 4.6 has enough public results to be ranked (#19); AI Co-Mathematician does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/ai-co-mathematician-vs-grok-4-6
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. AI Co-Mathematician scores higher in 1 category and Grok 4.6 in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in math, where AI Co-Mathematician leads 71.7 to 66.8.
- The biggest single-benchmark swing is FrontierMath Tier 4: 75.6% for AI Co-Mathematician and 31.7% for Grok 4.6.

## Snapshot

| | AI Co-Mathematician | Grok 4.6 |
|---|---|---|
| Provider | Google | xAI |
| Noometry Index | 57.6 | 56.8 |
| Rank | — | 19 |
| Context | — | 500K |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Proprietary | Proprietary |

## Coding

- AI Co-Mathematician: —
- Grok 4.6: 58.0 (#14)

| Benchmark | AI Co-Mathematician | Grok 4.6 |
|---|---|---|
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| CursorBench | — | 41.4% |
| LMArena WebDev | — | 1620 |
| FrontierSWE | — | 25.3% |
| SciCode | — | 56.5% |
| WeirdML | — | 67.3% |
| LMArena Coding | — | 1464 |
| ALE-Bench | — | 1,508 |

## Agentic & Tool Use

- AI Co-Mathematician: —
- Grok 4.6: 39.4 (#25)

| Benchmark | AI Co-Mathematician | Grok 4.6 |
|---|---|---|
| APEX-Agents | — | 65.3% |
| GDP.pdf | — | 17.2% |
| Vending-Bench 2 | — | 9,047 |

## Reasoning

- AI Co-Mathematician: —
- Grok 4.6: 61.3 (#18)

| Benchmark | AI Co-Mathematician | Grok 4.6 |
|---|---|---|
| ARC-AGI-2 | — | 67.1% |
| SimpleBench | — | 75.9% |
| NYT Connections (extended) | — | 80% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 19.7% |
| Chess Puzzles | — | 40% |
| EBR-Bench | — | 30.5% |
| LMArena Hard Prompts | — | 1445 |
| Mystery Game Puzzles | — | 34% |
| DTBench | — | 97.3% |
| LMCA | — | 48.5% |
| Epoch Capabilities Index | — | 156.48 |

## Math

- AI Co-Mathematician: 71.7
- Grok 4.6: 66.8 (#19)

| Benchmark | AI Co-Mathematician | Grok 4.6 |
|---|---|---|
| FrontierMath Tier 4 | 75.6% | 31.7% |
| FrontierMath (Tiers 1-3) | — | 66% |
| OTIS Mock AIME 2024-2025 | — | 99.2% |
| ProofBench | — | 51% |
| LMArena Math | — | 1416 |
| FrontierMath Tier 4 (v1) | 47.9% | — |

## Knowledge

- AI Co-Mathematician: —
- Grok 4.6: 63.3 (#18)

| Benchmark | AI Co-Mathematician | Grok 4.6 |
|---|---|---|
| GPQA Diamond | — | 94% |
| SimpleQA Verified | — | 49.3% |
| LMArena Expert | — | 1463 |

## Multimodal

- AI Co-Mathematician: —
- Grok 4.6: 43.9 (#18)

| Benchmark | AI Co-Mathematician | Grok 4.6 |
|---|---|---|
| LMArena Vision | — | 1265 |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
| LMArena Document | — | 1452 |

## Multilingual

- AI Co-Mathematician: —
- Grok 4.6: 53.3 (#67)

| Benchmark | AI Co-Mathematician | Grok 4.6 |
|---|---|---|
| LMArena Non-English | — | 1422 |
| LMArena Chinese | — | 1479 |
| LMArena French | — | 1458 |
| LMArena German | — | 1425 |
| LMArena Japanese | — | 1383 |
| LMArena Korean | — | 1395 |
| LMArena Russian | — | 1427 |
| LMArena Spanish | — | 1408 |

## Instruction Following

- AI Co-Mathematician: —
- Grok 4.6: 75.6 (#59)

| Benchmark | AI Co-Mathematician | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | — | 1431 |

## Long Context

- AI Co-Mathematician: —
- Grok 4.6: 44.4 (#62)

| Benchmark | AI Co-Mathematician | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | — | 1453 |

## Writing & Preference

- AI Co-Mathematician: —
- Grok 4.6: 62.5 (#77)

| Benchmark | AI Co-Mathematician | Grok 4.6 |
|---|---|---|
| LMArena Text | — | 1427 |
| LMArena Creative Writing | — | 1430 |
| LMArena Multi-Turn | — | 1422 |

## FAQ

### Is AI Co-Mathematician better than Grok 4.6?

Grok 4.6 has enough public results to be ranked (#19); AI Co-Mathematician does not yet, so treat this comparison as directional.

### How many benchmarks do AI Co-Mathematician and Grok 4.6 share?

1 benchmark has published results for both models. AI Co-Mathematician has 2 scored results on Noometry and Grok 4.6 has 49.