GPT-5 Nano vs Mercury 2.5
GPT-5 Nano leads Mercury 2.5 on the Artificial Analysis Intelligence Index, 13.0 to 12.3, and Mercury 2.5 costs 2.7x less per output token ($0.15 vs $0.40 per million). Updated October 22, 2026; 7 benchmarks have a result for both.
GPT-5 Nano or Mercury 2.5: which to pick
Only Mercury 2.5 has a coding score, 1.6 on the Vibe Coding Index; GPT-5 Nano has none, so the two cannot be ranked on coding.
Pick GPT-5 Nano for a larger context window (400K against 260K tokens) and work measured by AA Intelligence Index or ProofBench, where it leads.
- Shared results
- 7
- GPT-5 Nano only
- 80
- Mercury 2.5 only
- 15
- Like-for-like categories
- 5 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
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
GPT-5 Nano
GPT-5 Nano leads, 13.0 against 12.3.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only GPT-5 Nano has a GPQA Diamond result, 63.4%.
Directional only
Math
AIME
No call
Only GPT-5 Nano has a AIME result, 81.2%.
Directional only
Knowledge
MMLU Pro
No call
Only GPT-5 Nano has a MMLU Pro result, 76.1%.
Directional only
Web design
Design Arena: websites
No call
Only GPT-5 Nano has a Design Arena: websites result, 1101.
Directional only
Long documents
Listed context window
GPT-5 Nano
GPT-5 Nano takes 400K tokens against 260K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mercury 2.5
GPT-5 Nano $0.0003, Mercury 2.5 $0.0001 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5 Nano has the number, $0.109.
Directional only
At a glance
- Coding index
- GPT-5 Nano not benchmarked, Mercury 2.5 1.6 from 2 benchmarks.
- Widest category
- General, 22.2 points apart on average over 2 shared benchmarks.
- Widest single gap
- LegalBench (Vals AI): GPT-5 Nano 50.1% against Mercury 2.5 83.1%, 32.9 points apart on a 0 to 100 scale.
- Output price
- GPT-5 Nano $0.40 against Mercury 2.5 $0.15 per million output tokens, 2.7x apart.
- Context window
- GPT-5 Nano takes 400K tokens, Mercury 2.5 260K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | GPT-5 Nano | Bars | Mercury 2.5 | Ties |
|---|---|---|---|---|
| Intelligence | 1 | 0 | ||
| Reasoning | 0 | 1 | ||
| Math | 1 | 0 | ||
| Knowledge | 0 | 2 | ||
| General | 1 | 1 | ||
| All shared boards | 3 | 4 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index17 boards, none shared
| Benchmark | GPT-5 Nano | Mercury 2.5 | Leader |
|---|---|---|---|
| SWE-bench Verified | 34.8% | Not measured | Only GPT-5 Nano measured |
| LiveCodeBench (Vals AI) | 70.2% | Not measured | Only GPT-5 Nano 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 |
| LiveCodeBench (Artificial Analysis run) | 78.9% | Not measured | Only GPT-5 Nano measured |
| SciCode | Not measured | 38.5% | Only Mercury 2.5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 17.4% | Not measured | Only GPT-5 Nano measured |
| Terminal-Bench | 21.8% | Not measured | Only GPT-5 Nano measured |
| WeirdML | 38.1% | Not measured | Only GPT-5 Nano measured |
| ALE-Bench | Not measured | 301.6 | Only Mercury 2.5 measured |
| LMArena Text: coding | 1351 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: software and IT | 1345 | Not measured | Only GPT-5 Nano measured |
| Neither model has a result on the other 22 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5 Nano | Mercury 2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 13.0 | 12.3 | GPT-5 Nano |
| Epoch Capabilities Index | 139.2 | Not measured | Only GPT-5 Nano measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | GPT-5 Nano | 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 |
| τ²-Bench Telecom | 36.5% | Not measured | Only GPT-5 Nano measured |
| Berkeley Function Calling Leaderboard (BFCL) | 51.4% | Not measured | Only GPT-5 Nano measured |
| Neither model has a result on the other 34 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-5 Nano | Mercury 2.5 | Leader |
|---|---|---|---|
| GPQA Diamond | 63.4% | Not measured | Only GPT-5 Nano measured |
| MMMU Pro (Vals AI) | 70.9% | Not measured | Only GPT-5 Nano measured |
| GPQA Diamond (Artificial Analysis run) | 67.6% | Not measured | Only GPT-5 Nano measured |
| Humanity's Last Exam (Artificial Analysis run) | 9.5% | 11.8% | Mercury 2.5 |
| GPQA Diamond (Epoch AI run) | 69.4% | Not measured | Only GPT-5 Nano measured |
| ARC-AGI | 20.7% | Not measured | Only GPT-5 Nano measured |
| ARC-AGI-2 | 2.6% | Not measured | Only GPT-5 Nano measured |
| Chess puzzles | 22.0% | Not measured | Only GPT-5 Nano measured |
| Mystery game puzzles | 9.0% | Not measured | Only GPT-5 Nano measured |
| VPCT | 37.2% | Not measured | Only GPT-5 Nano measured |
| LMArena Text: hard prompts | 1328 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: expert | 1321 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: hard prompts in English | 1338 | Not measured | Only GPT-5 Nano measured |
| LMArena Vision: diagrams | 1141 | Not measured | Only GPT-5 Nano measured |
| LMArena Vision: homework | 1157 | Not measured | Only GPT-5 Nano measured |
| Kagi LLM Benchmark | 62.2% | Not measured | Only GPT-5 Nano measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5 Nano | Mercury 2.5 | Leader |
|---|---|---|---|
| AIME | 81.2% | Not measured | Only GPT-5 Nano measured |
| MATH 500 (Vals AI) | 93.8% | Not measured | Only GPT-5 Nano measured |
| MGSM (Vals AI) | 89.3% | Not measured | Only GPT-5 Nano measured |
| AA Math Index | 83.7 | Not measured | Only GPT-5 Nano measured |
| AIME 2025 (Artificial Analysis run) | 83.7% | Not measured | Only GPT-5 Nano measured |
| OTIS Mock AIME | 81.1% | Not measured | Only GPT-5 Nano measured |
| FrontierMath, tiers 1 to 3 | 20.0% | Not measured | Only GPT-5 Nano measured |
| FrontierMath, tier 4 | 2.4% | Not measured | Only GPT-5 Nano measured |
| ProofBench | 12.0% | 3.0% | GPT-5 Nano |
| MATH level 5 | 95.2% | Not measured | Only GPT-5 Nano measured |
| LMArena Text: math | 1317 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: mathematical work | 1326 | Not measured | Only GPT-5 Nano measured |
| Neither model has a result on the other 1 board here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-5 Nano | Mercury 2.5 | Leader |
|---|---|---|---|
| MMLU Pro | 76.1% | Not measured | Only GPT-5 Nano measured |
| LegalBench (Vals AI) | 50.1% | 83.1% | Mercury 2.5 |
| CaseLaw (Vals AI) | 52.6% | Not measured | Only GPT-5 Nano measured |
| TaxEval (Vals AI) | 67.4% | Not measured | Only GPT-5 Nano measured |
| MortgageTax (Vals AI) | 53.6% | Not measured | Only GPT-5 Nano measured |
| MedQA (Vals AI) | 93.3% | Not measured | Only GPT-5 Nano measured |
| MedCode (Vals AI) | 30.4% | 31.3% | Mercury 2.5 |
| MMLU Pro (Artificial Analysis run) | 78.0% | Not measured | Only GPT-5 Nano measured |
| SimpleQA Verified | 11.7% | Not measured | Only GPT-5 Nano measured |
| LMArena Text: science | 1318 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: medicine and healthcare | 1335 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: legal and government | 1298 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: business and finance | 1311 | Not measured | Only GPT-5 Nano measured |
| Neither model has a result on the other 5 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | GPT-5 Nano | Mercury 2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1101 | Not measured | Only GPT-5 Nano measured |
| Design Arena: UI components | 1064 | Not measured | Only GPT-5 Nano measured |
| Design Arena: game dev | 1044 | Not measured | Only GPT-5 Nano measured |
| Design Arena: data viz | 1056 | Not measured | Only GPT-5 Nano measured |
| Design Arena: 3D | 965 | Not measured | Only GPT-5 Nano measured |
| Design Arena: all code categories | 1084 | Not measured | Only GPT-5 Nano measured |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | GPT-5 Nano | Mercury 2.5 | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | Not measured | 45.3% | Only Mercury 2.5 measured |
| SAGE (Vals AI) | 30.4% | Not measured | Only GPT-5 Nano measured |
| MedScribe (Vals AI) | 72.9% | 55.1% | GPT-5 Nano |
| IFBench | 67.6% | Not measured | Only GPT-5 Nano measured |
| Long context reasoning (AA-LCR) | 45.0% | 71.7% | Mercury 2.5 |
| DTBench | 62.7% | Not measured | Only GPT-5 Nano measured |
| LMCA | 7.9% | Not measured | Only GPT-5 Nano measured |
| Fiction.LiveBench | 44.4% | Not measured | Only GPT-5 Nano measured |
| LMArena Text | 1320 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: instruction following | 1306 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: creative writing | 1249 | Not measured | Only GPT-5 Nano measured |
| LMArena Vision | 1159 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: English | 1321 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: non-English | 1313 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: Chinese | 1356 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: German | 1327 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: Japanese | 1227 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: Korean | 1269 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: Spanish | 1360 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: Russian | 1296 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: Polish | 1314 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: multi-turn | 1311 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: longer queries | 1312 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: writing and language | 1283 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: entertainment and media | 1268 | Not measured | Only GPT-5 Nano measured |
| LMArena Vision: English | 1170 | Not measured | Only GPT-5 Nano measured |
| LMArena Vision: Chinese | 1176 | Not measured | Only GPT-5 Nano measured |
| LMArena Vision: reading text | 1152 | Not measured | Only GPT-5 Nano measured |
| LMArena Vision: humor | 1110 | Not measured | Only GPT-5 Nano measured |
| Neither model has a result on the other 17 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5 Nano | Mercury 2.5 | Leader |
|---|---|---|---|
| Neither model has a result on 5 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 | OpenAI GPT-5 Nano | Inception Mercury 2.5 |
|---|---|---|
| Maker | OpenAI | Inception |
| Weights | No public weights listed | No public weights listed |
| Released | August 7, 2025 | September 8, 2026 |
| Context window | 400K | 260K |
| Input $/Mtok | $0.05 | $0.04 |
| Output $/Mtok | $0.40 | $0.15 |
| Coding index | Not benchmarked | 1.6 |
| Independent measurements behind it | 0 | 2 |
| Cost per solved task | $0.109 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5 Nano better than Mercury 2.5 for coding?
Only Mercury 2.5 has a coding score, 1.6 on the Vibe Coding Index; GPT-5 Nano has none, so the two cannot be ranked on coding. Pick GPT-5 Nano for a larger context window (400K against 260K tokens) and work measured by AA Intelligence Index or ProofBench, where it leads.
Which is cheaper, GPT-5 Nano or Mercury 2.5?
GPT-5 Nano costs $0.05 per million input tokens and $0.40 per million output tokens; Mercury 2.5 costs $0.04 and $0.15. Cost per solved task is known for GPT-5 Nano only.
Which has the bigger context window, GPT-5 Nano or Mercury 2.5?
GPT-5 Nano, with 400K tokens against 260K.
How many benchmarks is the GPT-5 Nano vs Mercury 2.5 comparison based on?
7 benchmarks have a result for both models as of October 22, 2026. GPT-5 Nano's coding index rests on 0 independent benchmarks and Mercury 2.5's on 2. Where only one model has a result, the page says so instead of naming a winner.