GPT-5.4 vs Mercury 2
Updated October 21, 2026. 40 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick GPT-5.4 for coding: it scores 37.7 on the Vibe Coding Index against 0.0 for Mercury 2.
Pick Mercury 2 when output tokens cost 20.0x less.
- Shared results
- 40
- GPT-5.4 only
- 69
- Mercury 2 only
- 2
- Like-for-like categories
- 7 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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, four public coding benchmarks
GPT-5.4
GPT-5.4 scores 37.7 against 0.0.
One benchmark behind each score
Intelligence
AA Intelligence Index
GPT-5.4
GPT-5.4 leads, 39.0 against 10.8.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Mercury 2 has a AA Agentic Index result, 1.6.
Directional only
Reasoning
GPQA Diamond
No call
Only GPT-5.4 has a GPQA Diamond result, 91.7%.
Directional only
Math
AIME
No call
Only GPT-5.4 has a AIME result, 96.7%.
Directional only
Knowledge
MMLU Pro
No call
Only GPT-5.4 has a MMLU Pro result, 87.5%.
Directional only
Web design
Design Arena: websites
GPT-5.4
GPT-5.4 leads, 1199 against 1036.
Same board, both measured
Long documents
Listed context window
GPT-5.4
GPT-5.4 takes 1.05M tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mercury 2
GPT-5.4 $0.010, Mercury 2 $0.0006 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.4 has the number, $1.02.
Directional only
At a glance
- Coding index
- GPT-5.4 37.7 from 1 benchmark, Mercury 2 0.0 from 1 benchmark.
- Widest category
- Coding, 33.5 points apart on average over 9 shared benchmarks.
- Widest single gap
- LMArena WebDev: React: GPT-5.4 1454 against Mercury 2 1160, 49.0 points apart on a 0 to 100 scale.
- Output price
- GPT-5.4 $15.00 against Mercury 2 $0.75 per million output tokens, 20.0x apart.
- Context window
- GPT-5.4 takes 1.05M tokens, Mercury 2 128K.
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-5.4 | Bars | Mercury 2 | Ties |
|---|---|---|---|---|
| Coding | 9 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 5 | 0 | ||
| Knowledge | 3 | 0 | ||
| Web design | 8 | 0 | ||
| General | 13 | 0 | ||
| All shared boards | 40 | 0 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index90
| Benchmark | GPT-5.4 | Mercury 2 | Leader |
|---|---|---|---|
| LMArena WebDev | 1464 | 1171 | GPT-5.4 |
| AA Coding Index | 71.1 | 31.1 | GPT-5.4 |
| LiveCodeBench (Vals AI) | 84.1% | Not measured | Only GPT-5.4 measured |
| SWE-bench Verified (Vals AI) | 78.2% | Not measured | Only GPT-5.4 measured |
| Vibe Code Bench (Vals AI) | 67.4% | Not measured | Only GPT-5.4 measured |
| Code migration (Vals AI) | 35.0% | Not measured | Only GPT-5.4 measured |
| ProgramBench (Vals AI) | 0.5% | Not measured | Only GPT-5.4 measured |
| SkillsBench (Vals AI) | 51.7% | Not measured | Only GPT-5.4 measured |
| SciCode | Not measured | 37.7% | Only Mercury 2 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 57.6% | 26.5% | GPT-5.4 |
| Terminal-Bench | 81.8% | Not measured | Only GPT-5.4 measured |
| GSO-Bench | 31.4% | Not measured | Only GPT-5.4 measured |
| WeirdML | 77.7% | 43.2% | GPT-5.4 |
| MirrorCode | 15.6% | Not measured | Only GPT-5.4 measured |
| ALE-Bench | 1607.0 | 785.6 | GPT-5.4 |
| LMArena Text: coding | 1496 | 1390 | GPT-5.4 |
| LMArena Text: software and IT | 1491 | 1385 | GPT-5.4 |
| LMArena WebDev: React | 1454 | 1160 | GPT-5.4 |
| LMArena WebDev: HTML | 1478 | 1199 | GPT-5.4 |
| LMArena WebDev: from an image | 1436 | Not measured | Only GPT-5.4 measured |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5.4 | Mercury 2 | Leader |
|---|---|---|---|
| AA Intelligence Index | 39.0 | 10.8 | GPT-5.4 |
| Epoch Capabilities Index | 157.3 | Not measured | Only GPT-5.4 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5.4 | Mercury 2 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 1.6 | Only Mercury 2 measured |
| Design Arena: agents building web apps | 1059 | Not measured | Only GPT-5.4 measured |
| Design Arena: agents building full-stack apps | 1017 | Not measured | Only GPT-5.4 measured |
| Design Arena: agents building mobile apps | 1087 | Not measured | Only GPT-5.4 measured |
| Design Arena: agents building Android apps | 1037 | Not measured | Only GPT-5.4 measured |
| Design Arena: agents building Godot games | 1135 | Not measured | Only GPT-5.4 measured |
| τ²-Bench Telecom | 87.1% | 70.8% | GPT-5.4 |
| APEX-Agents | 52.4% | Not measured | Only GPT-5.4 measured |
| METR time horizons | 74.3% | Not measured | Only GPT-5.4 measured |
| DeepResearch Bench | 35.1% | Not measured | Only GPT-5.4 measured |
| PostTrainBench | 19.0% | Not measured | Only GPT-5.4 measured |
| Vending-Bench 2 | $6,144 | Not measured | Only GPT-5.4 measured |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | GPT-5.4 | Mercury 2 | Leader |
|---|---|---|---|
| GPQA Diamond | 91.7% | Not measured | Only GPT-5.4 measured |
| MMMU Pro (Vals AI) | 87.5% | Not measured | Only GPT-5.4 measured |
| GPQA Diamond (Artificial Analysis run) | 92.0% | 77.0% | GPT-5.4 |
| Humanity's Last Exam (Artificial Analysis run) | 43.7% | 17.1% | GPT-5.4 |
| GPQA Diamond (Epoch AI run) | 93.3% | Not measured | Only GPT-5.4 measured |
| ARC-AGI | 93.7% | Not measured | Only GPT-5.4 measured |
| ARC-AGI-2 | 74.0% | Not measured | Only GPT-5.4 measured |
| Chess puzzles | 48.0% | Not measured | Only GPT-5.4 measured |
| Mystery game puzzles | 37.0% | Not measured | Only GPT-5.4 measured |
| EBR-bench | 25.4% | Not measured | Only GPT-5.4 measured |
| LMArena Text: hard prompts | 1485 | 1362 | GPT-5.4 |
| LMArena Text: expert | 1507 | 1358 | GPT-5.4 |
| LMArena Text: hard prompts in English | 1479 | 1374 | GPT-5.4 |
| LMArena Vision: diagrams | 1327 | Not measured | Only GPT-5.4 measured |
| LMArena Vision: homework | 1336 | Not measured | Only GPT-5.4 measured |
| Neither model has a result on the other 6 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | GPT-5.4 | Mercury 2 | Leader |
|---|---|---|---|
| AIME | 96.7% | Not measured | Only GPT-5.4 measured |
| OTIS Mock AIME | 97.8% | Not measured | Only GPT-5.4 measured |
| FrontierMath, tiers 1 to 3 | 78.6% | Not measured | Only GPT-5.4 measured |
| FrontierMath, tier 4 | 49.0% | Not measured | Only GPT-5.4 measured |
| ProofBench | 56.0% | Not measured | Only GPT-5.4 measured |
| LMArena Text: math | 1488 | Not measured | Only GPT-5.4 measured |
| LMArena Text: mathematical work | 1497 | Not measured | Only GPT-5.4 measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | GPT-5.4 | Mercury 2 | Leader |
|---|---|---|---|
| MMLU Pro | 87.5% | Not measured | Only GPT-5.4 measured |
| LegalBench (Vals AI) | 86.0% | Not measured | Only GPT-5.4 measured |
| CaseLaw (Vals AI) | 63.8% | Not measured | Only GPT-5.4 measured |
| CorpFin (Vals AI) | 65.3% | Not measured | Only GPT-5.4 measured |
| TaxEval (Vals AI) | 74.0% | Not measured | Only GPT-5.4 measured |
| MortgageTax (Vals AI) | 68.3% | Not measured | Only GPT-5.4 measured |
| MedQA (Vals AI) | 96.1% | Not measured | Only GPT-5.4 measured |
| MedCode (Vals AI) | 41.3% | Not measured | Only GPT-5.4 measured |
| SimpleQA Verified | 45.1% | Not measured | Only GPT-5.4 measured |
| LMArena Text: science | 1479 | 1343 | GPT-5.4 |
| LMArena Text: medicine and healthcare | 1458 | 1363 | GPT-5.4 |
| LMArena Text: legal and government | 1486 | Not measured | Only GPT-5.4 measured |
| LMArena Text: business and finance | 1474 | 1349 | GPT-5.4 |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | GPT-5.4 | Mercury 2 | Leader |
|---|---|---|---|
| Design Arena: websites | 1199 | 1036 | GPT-5.4 |
| Design Arena: UI components | 1215 | 998 | GPT-5.4 |
| Design Arena: game dev | 1195 | 985 | GPT-5.4 |
| Design Arena: data viz | 1196 | 1009 | GPT-5.4 |
| Design Arena: 3D | 1065 | 982 | GPT-5.4 |
| Design Arena: all code categories | 1180 | 1022 | GPT-5.4 |
| Design Arena: SVG | 1141 | 998 | GPT-5.4 |
| Design Arena: ASCII art | 1188 | 990 | GPT-5.4 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index130
| Benchmark | GPT-5.4 | Mercury 2 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 43.3% | Not measured | Only GPT-5.4 measured |
| MedScribe (Vals AI) | 77.5% | Not measured | Only GPT-5.4 measured |
| IFBench | 73.9% | 69.8% | GPT-5.4 |
| Long context reasoning (AA-LCR) | 82.0% | 43.7% | GPT-5.4 |
| DTBench | 94.4% | Not measured | Only GPT-5.4 measured |
| LMCA | 52.0% | Not measured | Only GPT-5.4 measured |
| CL-bench | 27.9% | Not measured | Only GPT-5.4 measured |
| Furniture assembly | 37.5% | Not measured | Only GPT-5.4 measured |
| CL-bench Life | 21.7% | Not measured | Only GPT-5.4 measured |
| LMArena Text | 1469 | 1354 | GPT-5.4 |
| LMArena Text: instruction following | 1469 | 1328 | GPT-5.4 |
| LMArena Text: creative writing | 1439 | 1286 | GPT-5.4 |
| LMArena Vision | 1303 | Not measured | Only GPT-5.4 measured |
| LMArena Text: English | 1467 | 1378 | GPT-5.4 |
| LMArena Text: non-English | 1465 | 1330 | GPT-5.4 |
| LMArena Text: Chinese | 1520 | 1414 | GPT-5.4 |
| LMArena Text: German | 1472 | Not measured | Only GPT-5.4 measured |
| LMArena Text: Japanese | 1485 | Not measured | Only GPT-5.4 measured |
| LMArena Text: Korean | 1449 | Not measured | Only GPT-5.4 measured |
| LMArena Text: French | 1493 | Not measured | Only GPT-5.4 measured |
| LMArena Text: Spanish | 1452 | Not measured | Only GPT-5.4 measured |
| LMArena Text: Russian | 1480 | 1304 | GPT-5.4 |
| LMArena Text: Polish | 1472 | Not measured | Only GPT-5.4 measured |
| LMArena Text: multi-turn | 1482 | 1357 | GPT-5.4 |
| LMArena Text: longer queries | 1473 | 1329 | GPT-5.4 |
| LMArena Text: writing and language | 1458 | 1300 | GPT-5.4 |
| LMArena Text: entertainment and media | 1438 | 1314 | GPT-5.4 |
| LMArena Vision: English | 1301 | Not measured | Only GPT-5.4 measured |
| LMArena Vision: Chinese | 1354 | Not measured | Only GPT-5.4 measured |
| LMArena Vision: reading text | 1312 | Not measured | Only GPT-5.4 measured |
| LMArena Vision: humor | 1284 | Not measured | Only GPT-5.4 measured |
| LMArena Vision: recognizing things | 1251 | Not measured | Only GPT-5.4 measured |
| LMArena Vision: creative writing | 1283 | Not measured | Only GPT-5.4 measured |
| LMArena Document | 1471 | Not measured | Only GPT-5.4 measured |
| Neither model has a result on the other 12 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.4 | Mercury 2 | 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 costs less
Repository review
50K input + 3K output tokens
Mercury 2 costs less
Agent loop
200K input + 10K output tokens
Mercury 2 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-5.4 | Inception Mercury 2 |
|---|---|---|
| Maker | OpenAI | Inception |
| Weights | No public weights listed | No public weights listed |
| Released | March 5, 2026 | March 4, 2026 |
| Context window | 1.05M | 128K |
| Input $/Mtok | $2.50 | $0.25 |
| Output $/Mtok | $15.00 | $0.75 |
| Coding index | 37.7 | 0.0 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | $1.02 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.4 better than Mercury 2 for coding?
Pick GPT-5.4 for coding: it scores 37.7 on the Vibe Coding Index against 0.0 for Mercury 2. Pick Mercury 2 when output tokens cost 20.0x less.
Which is cheaper, GPT-5.4 or Mercury 2?
GPT-5.4 costs $2.50 per million input tokens and $15.00 per million output tokens; Mercury 2 costs $0.25 and $0.75. Cost per solved task is known for GPT-5.4 only.
Which has the bigger context window, GPT-5.4 or Mercury 2?
GPT-5.4, with 1.05M tokens against 128K.
How many benchmarks is the GPT-5.4 vs Mercury 2 comparison based on?
40 benchmarks have a result for both models as of October 21, 2026. GPT-5.4's coding index rests on 1 independent benchmark and Mercury 2's on 1. Where only one model has a result, the page says so instead of naming a winner.