Model comparison
DeepSeek V4 Flash vs Mercury
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 37.6 on the Noometry Index.
Last verified . 9 shared benchmarks.
DeepSeekSummary
- They share 9 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 6 categories and Mercury in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 17.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 52.2% for DeepSeek V4 Flash and 21.6% for Mercury.
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Flash | Mercury | |
|---|---|---|
| Provider | DeepSeek | Inception |
| Noometry Index | 53.6 | 37.6 |
| Released | 2026-04-24 | — |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 41 | 9 |
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), Mercury: 38.7 (#170)
| Benchmark | DeepSeek V4 Flash | Mercury |
|---|---|---|
| LMArena Coding | 1457 | 1322 |
| FrontierCode | 18.8% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 49.9% | — |
| WeirdML | 63% | — |
| ALE-Bench | 1,306 | — |
Reasoning DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.7 (#30), Mercury: 17.5 (#293)
| Benchmark | DeepSeek V4 Flash | Mercury |
|---|---|---|
| Kagi LLM Benchmark | 52.2% | 21.6% |
| LMArena Hard Prompts | 1444 | 1285 |
| ARC-AGI-2 | 61.4% | — |
| SimpleBench | 61.1% | — |
| 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 Not comparable
DeepSeek V4 Flash: 60.3 (#37), Mercury: —
| Benchmark | DeepSeek V4 Flash | Mercury |
|---|---|---|
| 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% | — |
| LMArena Math | 1427 | — |
Knowledge Not comparable
DeepSeek V4 Flash: 55.4 (#48), Mercury: —
| Benchmark | DeepSeek V4 Flash | Mercury |
|---|---|---|
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 33.6% | — |
| LMArena Expert | 1441 | — |
Multilingual DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.0 (#72), Mercury: 41.6 (#206)
| Benchmark | DeepSeek V4 Flash | Mercury |
|---|---|---|
| LMArena Non-English | 1420 | 1260 |
| LMArena Chinese | 1468 | — |
| LMArena French | 1439 | — |
| LMArena German | 1418 | — |
| LMArena Japanese | 1406 | — |
| LMArena Korean | 1384 | — |
| LMArena Russian | 1428 | — |
| LMArena Spanish | 1436 | — |
Instruction Following DeepSeek V4 Flash leads
DeepSeek V4 Flash: 74.9 (#81), Mercury: 65.2 (#224)
| Benchmark | DeepSeek V4 Flash | Mercury |
|---|---|---|
| LMArena Instruction Following | 1421 | 1239 |
Long Context DeepSeek V4 Flash leads
DeepSeek V4 Flash: 43.8 (#85), Mercury: 38.4 (#198)
| Benchmark | DeepSeek V4 Flash | Mercury |
|---|---|---|
| LMArena Longer Query | 1434 | 1266 |
Writing & Preference DeepSeek V4 Flash leads
DeepSeek V4 Flash: 63.8 (#61), Mercury: 46.2 (#221)
| Benchmark | DeepSeek V4 Flash | Mercury |
|---|---|---|
| LMArena Text | 1432 | 1282 |
| LMArena Creative Writing | 1403 | 1191 |
| LMArena Multi-Turn | 1449 | 1282 |
| EQ-Bench Creative Writing | 1559 | — |
Frequently asked questions
Is DeepSeek V4 Flash better than Mercury?
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 37.6 on the Noometry Index.
Is DeepSeek V4 Flash or Mercury better for coding?
DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 38.7 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Flash and Mercury share?
9 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Mercury has 9.