# GPT-5.3 Chat vs Mercury 2

> GPT-5.3 Chat is the stronger model overall, scoring 42.1 to 38.8 on the Noometry Index. Mercury 2 costs 13× less per token, which makes it the better buy when GPT-5.3 Chat's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-3-chat-vs-mercury-2
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. GPT-5.3 Chat scores higher in 7 categories and Mercury 2 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5.3 Chat leads 63.3 to 54.0.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Chat.

## Snapshot

| | GPT-5.3 Chat | Mercury 2 |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 42.1 | 38.8 |
| Rank | 109 | 167 |
| Context | 128K | 128K |
| Input $/M | $1.75 | $0.25 |
| Output $/M | $14 | $0.75 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.3 Chat: 40.8 (#124)
- Mercury 2: 33.2 (#250)

| Benchmark | GPT-5.3 Chat | Mercury 2 |
|---|---|---|
| LMArena Coding | 1408 | 1391 |
| LMArena WebDev | — | 1170 |
| SciCode | — | 38.7% |
| WeirdML | — | 43.2% |
| ALE-Bench | — | 785.58 |

## Reasoning

- GPT-5.3 Chat: 27.3 (#105)
- Mercury 2: 23.0 (#170)

| Benchmark | GPT-5.3 Chat | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1399 | 1362 |
| CritPt | — | 0.8% |

## Math

- GPT-5.3 Chat: 35.4 (#146)
- Mercury 2: —

| Benchmark | GPT-5.3 Chat | Mercury 2 |
|---|---|---|
| LMArena Math | 1389 | — |

## Knowledge

- GPT-5.3 Chat: 38.2 (#137)
- Mercury 2: 35.6 (#170)

| Benchmark | GPT-5.3 Chat | Mercury 2 |
|---|---|---|
| LMArena Expert | 1397 | 1358 |
| Vectara Hallucination Rate | — | 12.3% |

## Multilingual

- GPT-5.3 Chat: 50.5 (#119)
- Mercury 2: 46.8 (#153)

| Benchmark | GPT-5.3 Chat | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1383 | 1331 |
| LMArena Chinese | 1433 | 1416 |
| LMArena Russian | 1400 | 1303 |
| LMArena French | 1398 | — |
| LMArena German | 1384 | — |
| LMArena Japanese | 1351 | — |
| LMArena Korean | 1347 | — |
| LMArena Spanish | 1371 | — |

## Instruction Following

- GPT-5.3 Chat: 73.0 (#124)
- Mercury 2: 70.4 (#161)

| Benchmark | GPT-5.3 Chat | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1378 | 1328 |

## Long Context

- GPT-5.3 Chat: 42.6 (#115)
- Mercury 2: 40.4 (#149)

| Benchmark | GPT-5.3 Chat | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1396 | 1329 |

## Writing & Preference

- GPT-5.3 Chat: 63.3 (#65)
- Mercury 2: 54.0 (#151)

| Benchmark | GPT-5.3 Chat | Mercury 2 |
|---|---|---|
| LMArena Text | 1389 | 1355 |
| LMArena Creative Writing | 1356 | 1289 |
| LMArena Multi-Turn | 1413 | 1358 |
| EQ-Bench Creative Writing | 1690 | — |

## FAQ

### Is GPT-5.3 Chat better than Mercury 2?

GPT-5.3 Chat is the stronger model overall, scoring 42.1 to 38.8 on the Noometry Index. Mercury 2 costs 13× less per token, which makes it the better buy when GPT-5.3 Chat's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.3 Chat or Mercury 2?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GPT-5.3 Chat lists at $1.75 and $14.

### Is GPT-5.3 Chat or Mercury 2 better for coding?

GPT-5.3 Chat scores higher on coding benchmarks: 40.8 versus 33.2 in the Noometry coding category.

### Which has the bigger context window?

Both accept 128K tokens.

### How many benchmarks do GPT-5.3 Chat and Mercury 2 share?

11 benchmarks have published results for both models. GPT-5.3 Chat has 18 scored results on Noometry and Mercury 2 has 17.