DeepSeek V3 vs Mercury 2.5
Mercury 2.5 costs 6.4x less per output token than DeepSeek V3 ($0.15 vs $0.9594 per million). Updated October 21, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.9594
- Coding
- 1.6
- Overall
- 12.3
- Output $/M
- $0.15
DeepSeek V3 or Mercury 2.5: which to pick
Only Mercury 2.5 has a coding score, 1.6 on the Vibe Coding Index; DeepSeek V3 has none, so the two cannot be ranked on coding.
Compare them on price, context and the boards below.
No benchmark has tested both yet. DeepSeek V3 has results on Aider polyglot, SWE-bench Lite and GPQA Diamond (Epoch AI run); Mercury 2.5 on Terminal-Bench 4 (Vals AI), Vibe Code Bench (Vals AI) and Code migration (Vals AI). Compare them on price and context instead.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only Mercury 2.5 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
No call
Only Mercury 2.5 has a AA Intelligence Index result, 12.3.
Directional only
Web design
Design Arena: websites
No call
Only DeepSeek V3 has a Design Arena: websites result, 1120.
Directional only
Long documents
Listed context window
Mercury 2.5
Mercury 2.5 takes 260K tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mercury 2.5
DeepSeek V3 $0.0008, Mercury 2.5 $0.0001 per turn.
List prices
At a glance
- Coding index
- DeepSeek V3 not benchmarked, Mercury 2.5 1.6 from 2 benchmarks.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- DeepSeek V3 $0.9594 against Mercury 2.5 $0.15 per million output tokens, 6.4x apart.
- Context window
- DeepSeek V3 takes 164K tokens, Mercury 2.5 260K.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index11 boards measured
| Benchmark | DeepSeek V3 | Mercury 2.5 | Leader |
|---|---|---|---|
| Aider polyglot | 70.2% | Not measured | Only DeepSeek V3 measured |
| SWE-bench Lite | 30.7% | Not measured | Only DeepSeek V3 measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 0.0% | Only Mercury 2.5 measured |
| Vibe Code Bench (Vals AI) | Not measured | 3.7% | Only Mercury 2.5 measured |
| Code migration (Vals AI) | Not measured | 4.5% | Only Mercury 2.5 measured |
| IOI (Vals AI) | Not measured | 2.4% | Only Mercury 2.5 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 34.5% | Only Mercury 2.5 measured |
| SkillsBench (Vals AI) | Not measured | 18.1% | Only Mercury 2.5 measured |
| CyberBench (Vals AI) | Not measured | 45.5% | Only Mercury 2.5 measured |
| SciCode | Not measured | 38.5% | Only Mercury 2.5 measured |
| ALE-Bench | Not measured | 301.6 | Only Mercury 2.5 measured |
| Neither model has a result on the other 27 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | DeepSeek V3 | Mercury 2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 12.3 | Only Mercury 2.5 measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | DeepSeek V3 | Mercury 2.5 | Leader |
|---|---|---|---|
| Finance Agent (Vals AI) | Not measured | 18.9% | Only Mercury 2.5 measured |
| Tax Agent Bench (Vals AI) | Not measured | 2.5% | Only Mercury 2.5 measured |
| Legal Research Bench (Vals AI) | Not measured | 4.3% | Only Mercury 2.5 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 8.8% | Only Mercury 2.5 measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 0.0% | Only Mercury 2.5 measured |
| Neither model has a result on the other 34 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | DeepSeek V3 | Mercury 2.5 | Leader |
|---|---|---|---|
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 11.8% | Only Mercury 2.5 measured |
| GPQA Diamond (Epoch AI run) | 71.2% | Not measured | Only DeepSeek V3 measured |
| Neither model has a result on the other 19 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | DeepSeek V3 | Mercury 2.5 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 48.9% | Not measured | Only DeepSeek V3 measured |
| ProofBench | Not measured | 3.0% | Only Mercury 2.5 measured |
| Neither model has a result on the other 11 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | DeepSeek V3 | Mercury 2.5 | Leader |
|---|---|---|---|
| LegalBench (Vals AI) | Not measured | 83.1% | Only Mercury 2.5 measured |
| MedCode (Vals AI) | Not measured | 31.3% | Only Mercury 2.5 measured |
| Neither model has a result on the other 15 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards measured
| Benchmark | DeepSeek V3 | Mercury 2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1120 | Not measured | Only DeepSeek V3 measured |
| Design Arena: UI components | 1093 | Not measured | Only DeepSeek V3 measured |
| Design Arena: game dev | 1053 | Not measured | Only DeepSeek V3 measured |
| Design Arena: data viz | 1089 | Not measured | Only DeepSeek V3 measured |
| Design Arena: 3D | 1087 | Not measured | Only DeepSeek V3 measured |
| Design Arena: all code categories | 1108 | Not measured | Only DeepSeek V3 measured |
| Design Arena: SVG | 976 | Not measured | Only DeepSeek V3 measured |
| Neither model has a result on the other 2 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | DeepSeek V3 | Mercury 2.5 | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | Not measured | 45.3% | Only Mercury 2.5 measured |
| MedScribe (Vals AI) | Not measured | 55.1% | Only Mercury 2.5 measured |
| Long context reasoning (AA-LCR) | Not measured | 71.7% | Only Mercury 2.5 measured |
| DTBench | 62.7% | Not measured | Only DeepSeek V3 measured |
| LMCA | 15.2% | Not measured | Only DeepSeek V3 measured |
| Neither model has a result on the other 41 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Mercury 2.5 costs less
Repository review
50K input + 3K output tokens
Mercury 2.5 costs less
Agent loop
200K input + 10K output tokens
Mercury 2.5 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | DeepSeek V3 | Inception Mercury 2.5 |
|---|---|---|
| Maker | DeepSeek | Inception |
| Weights | Open weights | No public weights listed |
| Released | December 26, 2024 | September 8, 2026 |
| Context window | 164K | 260K |
| Input $/Mtok | $0.2887 | $0.04 |
| Output $/Mtok | $0.9594 | $0.15 |
| Coding index | Not benchmarked | 1.6 |
| Independent measurements behind it | 0 | 2 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3 better than Mercury 2.5 for coding?
Only Mercury 2.5 has a coding score, 1.6 on the Vibe Coding Index; DeepSeek V3 has none, so the two cannot be ranked on coding. Compare them on price, context and the boards below.
Which is cheaper, DeepSeek V3 or Mercury 2.5?
DeepSeek V3 costs $0.2887 per million input tokens and $0.9594 per million output tokens; Mercury 2.5 costs $0.04 and $0.15. Cost per solved task is known for neither of them.
Which has the bigger context window, DeepSeek V3 or Mercury 2.5?
Mercury 2.5, with 260K tokens against 164K.
Has any benchmark tested both DeepSeek V3 and Mercury 2.5?
No benchmark has tested both yet. DeepSeek V3 has results on Aider polyglot, SWE-bench Lite and GPQA Diamond (Epoch AI run); Mercury 2.5 on Terminal-Bench 4 (Vals AI), Vibe Code Bench (Vals AI) and Code migration (Vals AI). Compare them on price and context instead. Data as of October 21, 2026.