Model comparison
DeepSeek V4.1 Flash vs Grok 4.20 (Non-Reasoning)
DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 48.5 on the Noometry Index.
Last verified . 22 shared benchmarks.
DeepSeekSummary
- They share 22 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 4 categories and Grok 4.20 (Non-Reasoning) in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.20 (Non-Reasoning) leads 52.8 to 41.6.
- The biggest single-benchmark swing is ProofBench: 54% for DeepSeek V4.1 Flash and 14% for Grok 4.20 (Non-Reasoning).
- 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 (Non-Reasoning).
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4.1 Flash | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 50.3 | 48.5 |
| Released | 2026-09-09 | 2026-02-17 |
| 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 | 25 | 46 |
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: 52.8 (#29), Grok 4.20 (Non-Reasoning): 41.8 (#104)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena WebDev | 1620 | 1374 |
| LMArena Coding | 1511 | 1458 |
| ALE-Bench | 1,092 | 1,150 |
| SciCode | 51.9% | — |
| WeirdML | — | 52.3% |
Agentic & Tool Use Not comparable
DeepSeek V4.1 Flash: —, Grok 4.20 (Non-Reasoning): 34.3 (#43)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |
Reasoning Grok 4.20 (Non-Reasoning) leads
DeepSeek V4.1 Flash: 46.2 (#39), Grok 4.20 (Non-Reasoning): 52.2 (#30)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| NYT Connections (extended) | 89.6% | 85.4% |
| LMArena Hard Prompts | 1485 | 1451 |
| DTBench | 89.9% | 90.1% |
| LMCA | 47% | 38.7% |
| Epoch Capabilities Index | 155.01 | 152.01 |
| ARC-AGI-2 | — | 65.1% |
| Kagi LLM Benchmark | — | 75% |
| ARC-AGI-1 | — | 89.5% |
| CritPt | 14.3% | — |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 63.8% |
| Surface Evolver Bench | 46.3% | — |
| ForecastBench | — | 61.4 |
Math Too close to call
DeepSeek V4.1 Flash: 48.4 (#52), Grok 4.20 (Non-Reasoning): 48.0 (#54)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| ProofBench | 54% | 14% |
| LMArena Math | 1493 | 1455 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
Knowledge Grok 4.20 (Non-Reasoning) leads
DeepSeek V4.1 Flash: 41.6 (#97), Grok 4.20 (Non-Reasoning): 52.8 (#54)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Expert | 1505 | 1440 |
| GPQA Diamond | — | 89.3% |
| SimpleQA Verified | — | 30.2% |
Multimodal Not comparable
DeepSeek V4.1 Flash: —, Grok 4.20 (Non-Reasoning): 33.2 (#88)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |
Multilingual Too close to call
DeepSeek V4.1 Flash: 55.5 (#29), Grok 4.20 (Non-Reasoning): 54.7 (#38)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1452 | 1440 |
| LMArena Chinese | 1506 | 1481 |
| LMArena French | 1448 | 1477 |
| LMArena Russian | 1473 | 1457 |
| LMArena Spanish | 1499 | 1442 |
| LMArena German | — | 1463 |
| LMArena Japanese | — | 1450 |
| LMArena Korean | — | 1417 |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.6 (#24), Grok 4.20 (Non-Reasoning): 75.0 (#79)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1475 | 1420 |
Long Context Too close to call
DeepSeek V4.1 Flash: 45.2 (#46), Grok 4.20 (Non-Reasoning): 45.4 (#33)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1476 | 1436 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
Writing & Preference Too close to call
DeepSeek V4.1 Flash: 65.8 (#43), Grok 4.20 (Non-Reasoning): 65.9 (#42)
| Benchmark | DeepSeek V4.1 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1465 | 1451 |
| LMArena Creative Writing | 1436 | 1439 |
| EQ-Bench Creative Writing | 1540 | 1574 |
| LMArena Multi-Turn | 1460 | 1456 |
Frequently asked questions
Is DeepSeek V4.1 Flash better than Grok 4.20 (Non-Reasoning)?
DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 48.5 on the Noometry Index.
Which is cheaper, DeepSeek V4.1 Flash or Grok 4.20 (Non-Reasoning)?
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 (Non-Reasoning) lists at $1.25 and $2.50.
Is DeepSeek V4.1 Flash or Grok 4.20 (Non-Reasoning) better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.8 versus 41.8 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 (Non-Reasoning) share?
22 benchmarks have published results for both models. DeepSeek V4.1 Flash has 25 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.