Model comparison
DeepSeek V4.1 Flash vs Grok 4.20 Multi-Agent
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 46.2 on the Noometry Index.
Last verified . 19 shared benchmarks.
DeepSeekSummary
- They share 19 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Grok 4.20 Multi-Agent in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 39.4.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 Multi-Agent.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4.1 Flash | Grok 4.20 Multi-Agent | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 52.8 | 46.2 |
| Released | 2026-09-09 | 2026-03-09 |
| Weights | Open | Proprietary |
| Context window | 1M | 1M |
| Max output | 393K | 30K |
| Input $ / M tokens | $0.15 | $1.25 |
| Output $ / M tokens | $0.60 | $2.50 |
| Results tracked | 37 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 52.9 (#32), Grok 4.20 Multi-Agent: 43.0 (#92)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Coding | 1506 | 1457 |
| LMArena WebDev | 1619 | — |
| SciCode | 51.9% | — |
| ALE-Bench | 1,092 | — |
Agentic & Tool Use Not comparable
DeepSeek V4.1 Flash: 31.2 (#69), Grok 4.20 Multi-Agent: —
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 Multi-Agent |
|---|---|---|
| APEX-Agents | 39.5% | — |
| GDP.pdf | 19.8% | — |
| LMArena Search | — | 1204 |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 50.2 (#36), Grok 4.20 Multi-Agent: 43.9 (#48)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 Multi-Agent |
|---|---|---|
| NYT Connections (extended) | 89.6% | 89.6% |
| LMArena Hard Prompts | 1483 | 1448 |
| CritPt | 14.3% | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 89.9% | — |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| Epoch Capabilities Index | 154.9 | — |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 66.7 (#25), Grok 4.20 Multi-Agent: 39.4 (#104)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Math | 1477 | 1442 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 54% | — |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 57.9 (#38), Grok 4.20 Multi-Agent: 40.4 (#119)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Expert | 1506 | 1445 |
| GPQA Diamond | 89.8% | — |
Multimodal Grok 4.20 Multi-Agent leads
DeepSeek V4.1 Flash: 39.1 (#61), Grok 4.20 Multi-Agent: 40.5 (#48)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Vision | 1277 | 1259 |
| Furniture Assembly | 34.2% | — |
Multilingual Too close to call
DeepSeek V4.1 Flash: 55.0 (#35), Grok 4.20 Multi-Agent: 54.4 (#43)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Non-English | 1448 | 1440 |
| LMArena Chinese | 1497 | 1475 |
| LMArena French | 1452 | 1466 |
| LMArena German | 1484 | 1456 |
| LMArena Japanese | 1412 | 1405 |
| LMArena Korean | 1452 | 1416 |
| LMArena Russian | 1471 | 1457 |
| LMArena Spanish | 1459 | 1447 |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.3 (#26), Grok 4.20 Multi-Agent: 74.8 (#84)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Instruction Following | 1474 | 1420 |
Long Context DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 45.2 (#47), Grok 4.20 Multi-Agent: 43.7 (#88)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Longer Query | 1475 | 1431 |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.4 (#48), Grok 4.20 Multi-Agent: 64.0 (#59)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Text | 1462 | 1450 |
| LMArena Creative Writing | 1435 | 1436 |
| LMArena Multi-Turn | 1457 | 1452 |
| EQ-Bench Creative Writing | 1540 | — |
Frequently asked questions
Is DeepSeek V4.1 Flash better than Grok 4.20 Multi-Agent?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 46.2 on the Noometry Index.
Which is cheaper, DeepSeek V4.1 Flash or Grok 4.20 Multi-Agent?
DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Grok 4.20 Multi-Agent lists at $1.25 and $2.50.
Is DeepSeek V4.1 Flash or Grok 4.20 Multi-Agent better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 43.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do DeepSeek V4.1 Flash and Grok 4.20 Multi-Agent share?
19 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Grok 4.20 Multi-Agent has 20.