Model comparison
DeepSeek V4 Flash vs Yi-Lightning
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 37.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and Yi-Lightning in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 25.9.
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Flash | Yi-Lightning | |
|---|---|---|
| Provider | DeepSeek | 01.AI |
| Noometry Index | 53.6 | 37.1 |
| Released | 2026-04-24 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 41 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Flash leads
DeepSeek V4 Flash: 47.9 (#59), Yi-Lightning: 27.4 (#320)
| Benchmark | DeepSeek V4 Flash | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1457 | 1312 |
| FrontierCode | 18.8% | — |
| Aider Polyglot | — | 12.9% |
| LMArena WebDev | 1582 | — |
| SciCode | 49.9% | — |
| WeirdML | 63% | — |
| ALE-Bench | 1,306 | — |
Reasoning DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.7 (#30), Yi-Lightning: 25.9 (#139)
| Benchmark | DeepSeek V4 Flash | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1444 | 1302 |
| ARC-AGI-2 | 61.4% | — |
| SimpleBench | 61.1% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | 89% | — |
| CritPt | 16.6% | — |
| Chess Puzzles | 33% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 90.9% | — |
| LMCA | 41.7% | — |
| Epoch Capabilities Index | 154.49 | — |
Math DeepSeek V4 Flash leads
DeepSeek V4 Flash: 60.3 (#37), Yi-Lightning: 36.2 (#172)
| Benchmark | DeepSeek V4 Flash | Yi-Lightning |
|---|---|---|
| LMArena Math | 1427 | 1300 |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| OTIS Mock AIME 2024-2025 | 94.4% | — |
| ProofBench | 56% | — |
Knowledge DeepSeek V4 Flash leads
DeepSeek V4 Flash: 55.4 (#48), Yi-Lightning: 35.4 (#185)
| Benchmark | DeepSeek V4 Flash | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1441 | 1286 |
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 33.6% | — |
Multilingual DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.0 (#72), Yi-Lightning: 42.2 (#196)
| Benchmark | DeepSeek V4 Flash | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1420 | 1269 |
| LMArena Chinese | 1468 | 1320 |
| LMArena French | 1439 | 1305 |
| LMArena German | 1418 | 1267 |
| LMArena Japanese | 1406 | 1228 |
| LMArena Korean | 1384 | 1192 |
| LMArena Russian | 1428 | 1255 |
| LMArena Spanish | 1436 | 1315 |
Instruction Following DeepSeek V4 Flash leads
DeepSeek V4 Flash: 74.9 (#81), Yi-Lightning: 67.4 (#196)
| Benchmark | DeepSeek V4 Flash | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1421 | 1278 |
Long Context DeepSeek V4 Flash leads
DeepSeek V4 Flash: 43.8 (#85), Yi-Lightning: 39.4 (#181)
| Benchmark | DeepSeek V4 Flash | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1434 | 1297 |
Writing & Preference DeepSeek V4 Flash leads
DeepSeek V4 Flash: 63.8 (#61), Yi-Lightning: 50.2 (#184)
| Benchmark | DeepSeek V4 Flash | Yi-Lightning |
|---|---|---|
| LMArena Text | 1432 | 1302 |
| LMArena Creative Writing | 1403 | 1280 |
| LMArena Multi-Turn | 1449 | 1311 |
| EQ-Bench Creative Writing | 1559 | — |
Frequently asked questions
Is DeepSeek V4 Flash better than Yi-Lightning?
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 37.1 on the Noometry Index.
Is DeepSeek V4 Flash or Yi-Lightning better for coding?
DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 27.4 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Flash and Yi-Lightning share?
17 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Yi-Lightning has 18.