Model comparison
DeepSeek-V3.1 vs Grok 4.3
DeepSeek-V3.1 and Grok 4.3 score almost the same on the Noometry Index (42.8 vs 43.8), so choose on price, context window or the category you care about most.
Last verified . 22 shared benchmarks.
DeepSeekSummary
- They share 22 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 3 categories and Grok 4.3 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.3 leads 52.5 to 43.7.
- The biggest single-benchmark swing is LMCA: 24.3% for DeepSeek-V3.1 and 38.3% for Grok 4.3.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $1.25 / $2.50 for Grok 4.3.
- Grok 4.3 accepts more context: 1M tokens versus 164K.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | Grok 4.3 | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 42.8 | 43.8 |
| Released | 2025-08-21 | 2026-04-17 |
| Weights | Open | Proprietary |
| Context window | 164K | 1M |
| Max output | 8K | 30K |
| Input $ / M tokens | $0.25 | $1.25 |
| Output $ / M tokens | $0.95 | $2.50 |
| Results tracked | 27 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.3 leads
DeepSeek-V3.1: 40.3 (#144), Grok 4.3: 41.6 (#121)
| Benchmark | DeepSeek-V3.1 | Grok 4.3 |
|---|---|---|
| WeirdML | 38.4% | 49.9% |
| LMArena Coding | 1417 | 1415 |
| LMArena WebDev | — | 1357 |
| SciCode | — | 47.3% |
| ALE-Bench | — | 944.17 |
Agentic & Tool Use Not comparable
DeepSeek-V3.1: —, Grok 4.3: 27.7 (#99)
| Benchmark | DeepSeek-V3.1 | Grok 4.3 |
|---|---|---|
| GDP.pdf | — | 8% |
| LMArena Search | — | 1165 |
| Vending-Bench 2 | — | 35.26 |
Reasoning Grok 4.3 leads
DeepSeek-V3.1: 27.9 (#110), Grok 4.3: 35.9 (#68)
| Benchmark | DeepSeek-V3.1 | Grok 4.3 |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1396 |
| DTBench | 82.7% | 90.7% |
| LMCA | 24.3% | 38.3% |
| Epoch Capabilities Index | 139.92 | 149.16 |
| ForecastBench | 58 | 60.3 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 55.2% |
| CritPt | — | 8% |
| Chess Puzzles | — | 25% |
Math Grok 4.3 leads
DeepSeek-V3.1: 38.9 (#122), Grok 4.3: 46.0 (#74)
| Benchmark | DeepSeek-V3.1 | Grok 4.3 |
|---|---|---|
| LMArena Math | 1420 | 1388 |
| FrontierMath (Tiers 1-3) | — | 42.8% |
| FrontierMath Tier 4 | — | 14.6% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | — | 11% |
Knowledge Grok 4.3 leads
DeepSeek-V3.1: 43.7 (#90), Grok 4.3: 52.5 (#62)
| Benchmark | DeepSeek-V3.1 | Grok 4.3 |
|---|---|---|
| LMArena Expert | 1405 | 1385 |
| GPQA Diamond | — | 88.8% |
| SimpleQA Verified | — | 33.2% |
| Vectara Hallucination Rate | 5.5% | — |
Multimodal Not comparable
DeepSeek-V3.1: —, Grok 4.3: 31.6 (#104)
| Benchmark | DeepSeek-V3.1 | Grok 4.3 |
|---|---|---|
| LMArena Vision | — | 1229 |
| Blueprint-Bench 2 | — | 0% |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Grok 4.3: 50.5 (#120)
| Benchmark | DeepSeek-V3.1 | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1400 | 1385 |
| LMArena Chinese | 1469 | 1422 |
| LMArena French | 1447 | 1412 |
| LMArena German | 1411 | 1395 |
| LMArena Japanese | 1378 | 1379 |
| LMArena Korean | 1337 | 1356 |
| LMArena Russian | 1405 | 1399 |
| LMArena Spanish | 1431 | 1398 |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), Grok 4.3: 72.1 (#140)
| Benchmark | DeepSeek-V3.1 | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1400 | 1366 |
Long Context Grok 4.3 leads
DeepSeek-V3.1: 36.3 (#232), Grok 4.3: 42.5 (#123)
| Benchmark | DeepSeek-V3.1 | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1422 | 1393 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Grok 4.3: 58.5 (#118)
| Benchmark | DeepSeek-V3.1 | Grok 4.3 |
|---|---|---|
| LMArena Text | 1420 | 1397 |
| LMArena Creative Writing | 1401 | 1380 |
| LMArena Multi-Turn | 1408 | 1406 |
| EQ-Bench Creative Writing | 1436 | — |
| EQ-Bench 4 | — | 1075 |
Frequently asked questions
Is DeepSeek-V3.1 better than Grok 4.3?
DeepSeek-V3.1 and Grok 4.3 score almost the same on the Noometry Index (42.8 vs 43.8), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-V3.1 or Grok 4.3?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Grok 4.3 lists at $1.25 and $2.50.
Is DeepSeek-V3.1 or Grok 4.3 better for coding?
Grok 4.3 scores higher on coding benchmarks: 41.6 versus 40.3 in the Noometry coding category.
Which has the bigger context window?
Grok 4.3 does, with 1M tokens against 164K.
How many benchmarks do DeepSeek-V3.1 and Grok 4.3 share?
22 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Grok 4.3 has 40.