Model comparison
GPT-5.3 Chat vs Mercury 2.5
GPT-5.3 Chat has enough public results to be ranked (#109); Mercury 2.5 does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in math, where GPT-5.3 Chat leads 35.4 to 22.4.
- Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Chat.
- Mercury 2.5 accepts more context: 260K tokens versus 128K.
Side by side
| GPT-5.3 Chat | Mercury 2.5 | |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 42.1 | 30.2 |
| Released | 2026-03-03 | 2026-09-08 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 260K |
| Max output | 16K | 66K |
| Input $ / M tokens | $1.75 | $0.04 |
| Output $ / M tokens | $14 | $0.15 |
| Results tracked | 18 | 2 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.3 Chat: 40.8 (#124), Mercury 2.5: —
| Benchmark | GPT-5.3 Chat | Mercury 2.5 |
|---|---|---|
| LMArena Coding | 1408 | — |
| ALE-Bench | — | 301.65 |
Reasoning Not comparable
GPT-5.3 Chat: 27.3 (#105), Mercury 2.5: —
| Benchmark | GPT-5.3 Chat | Mercury 2.5 |
|---|---|---|
| LMArena Hard Prompts | 1399 | — |
Math GPT-5.3 Chat leads
GPT-5.3 Chat: 35.4 (#146), Mercury 2.5: 22.4
| Benchmark | GPT-5.3 Chat | Mercury 2.5 |
|---|---|---|
| ProofBench | — | 3% |
| LMArena Math | 1389 | — |
Knowledge Not comparable
GPT-5.3 Chat: 38.2 (#137), Mercury 2.5: —
| Benchmark | GPT-5.3 Chat | Mercury 2.5 |
|---|---|---|
| LMArena Expert | 1397 | — |
Multilingual Not comparable
GPT-5.3 Chat: 50.5 (#119), Mercury 2.5: —
| Benchmark | GPT-5.3 Chat | Mercury 2.5 |
|---|---|---|
| LMArena Non-English | 1383 | — |
| LMArena Chinese | 1433 | — |
| LMArena French | 1398 | — |
| LMArena German | 1384 | — |
| LMArena Japanese | 1351 | — |
| LMArena Korean | 1347 | — |
| LMArena Russian | 1400 | — |
| LMArena Spanish | 1371 | — |
Instruction Following Not comparable
GPT-5.3 Chat: 73.0 (#124), Mercury 2.5: —
| Benchmark | GPT-5.3 Chat | Mercury 2.5 |
|---|---|---|
| LMArena Instruction Following | 1378 | — |
Long Context Not comparable
GPT-5.3 Chat: 42.6 (#115), Mercury 2.5: —
| Benchmark | GPT-5.3 Chat | Mercury 2.5 |
|---|---|---|
| LMArena Longer Query | 1396 | — |
Writing & Preference Not comparable
GPT-5.3 Chat: 63.3 (#65), Mercury 2.5: —
| Benchmark | GPT-5.3 Chat | Mercury 2.5 |
|---|---|---|
| LMArena Text | 1389 | — |
| LMArena Creative Writing | 1356 | — |
| EQ-Bench Creative Writing | 1690 | — |
| LMArena Multi-Turn | 1413 | — |
Frequently asked questions
Is GPT-5.3 Chat better than Mercury 2.5?
GPT-5.3 Chat has enough public results to be ranked (#109); Mercury 2.5 does not yet, so treat this comparison as directional.
Which is cheaper, GPT-5.3 Chat or Mercury 2.5?
Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; GPT-5.3 Chat lists at $1.75 and $14.
Which has the bigger context window?
Mercury 2.5 does, with 260K tokens against 128K.
How many benchmarks do GPT-5.3 Chat and Mercury 2.5 share?
0 benchmarks have published results for both models. GPT-5.3 Chat has 18 scored results on Noometry and Mercury 2.5 has 2.