Model comparison
AI Co-Mathematician vs DeepSeek V4.1 Flash
DeepSeek V4.1 Flash has enough public results to be ranked (#40); AI Co-Mathematician does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Google
DeepSeekSummary
- The widest gap is in math, where AI Co-Mathematician leads 71.7 to 48.4.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| AI Co-Mathematician | DeepSeek V4.1 Flash | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 57.6 | 50.3 |
| Released | 2026-05-08 | 2026-09-09 |
| Weights | Proprietary | Open |
| Context window | — | 1M |
| Max output | — | 393K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 2 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
AI Co-Mathematician: —, DeepSeek V4.1 Flash: 52.8 (#29)
| Benchmark | AI Co-Mathematician | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena WebDev | — | 1620 |
| SciCode | — | 51.9% |
| LMArena Coding | — | 1511 |
| ALE-Bench | — | 1,092 |
Reasoning Not comparable
AI Co-Mathematician: —, DeepSeek V4.1 Flash: 46.2 (#39)
| Benchmark | AI Co-Mathematician | DeepSeek V4.1 Flash |
|---|---|---|
| NYT Connections (extended) | — | 89.6% |
| CritPt | — | 14.3% |
| LMArena Hard Prompts | — | 1485 |
| DTBench | — | 89.9% |
| LMCA | — | 47% |
| Surface Evolver Bench | — | 46.3% |
| Epoch Capabilities Index | — | 155.01 |
Math AI Co-Mathematician leads
AI Co-Mathematician: 71.7, DeepSeek V4.1 Flash: 48.4 (#52)
| Benchmark | AI Co-Mathematician | DeepSeek V4.1 Flash |
|---|---|---|
| FrontierMath Tier 4 | 75.6% | — |
| ProofBench | — | 54% |
| LMArena Math | — | 1493 |
| FrontierMath Tier 4 (v1) | 47.9% | — |
Knowledge Not comparable
AI Co-Mathematician: —, DeepSeek V4.1 Flash: 41.6 (#97)
| Benchmark | AI Co-Mathematician | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Expert | — | 1505 |
Multilingual Not comparable
AI Co-Mathematician: —, DeepSeek V4.1 Flash: 55.5 (#29)
| Benchmark | AI Co-Mathematician | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Non-English | — | 1452 |
| LMArena Chinese | — | 1506 |
| LMArena French | — | 1448 |
| LMArena Russian | — | 1473 |
| LMArena Spanish | — | 1499 |
Instruction Following Not comparable
AI Co-Mathematician: —, DeepSeek V4.1 Flash: 77.6 (#24)
| Benchmark | AI Co-Mathematician | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1475 |
Long Context Not comparable
AI Co-Mathematician: —, DeepSeek V4.1 Flash: 45.2 (#46)
| Benchmark | AI Co-Mathematician | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Longer Query | — | 1476 |
Writing & Preference Not comparable
AI Co-Mathematician: —, DeepSeek V4.1 Flash: 65.8 (#43)
| Benchmark | AI Co-Mathematician | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Text | — | 1465 |
| LMArena Creative Writing | — | 1436 |
| EQ-Bench Creative Writing | — | 1540 |
| LMArena Multi-Turn | — | 1460 |
Frequently asked questions
Is AI Co-Mathematician better than DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash has enough public results to be ranked (#40); AI Co-Mathematician does not yet, so treat this comparison as directional.
How many benchmarks do AI Co-Mathematician and DeepSeek V4.1 Flash share?
0 benchmarks have published results for both models. AI Co-Mathematician has 2 scored results on Noometry and DeepSeek V4.1 Flash has 25.