Model comparison
GPT-6.1 Sol vs Mercury
Mercury has enough public results to be ranked (#192); GPT-6.1 Sol does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in coding, where GPT-6.1 Sol leads 51.4 to 38.1.
Side by side
| GPT-6.1 Sol | Mercury | |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 42.1 | 37.3 |
| Released | 2026-09-29 | — |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 2 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
GPT-6.1 Sol: 51.4, Mercury: 38.1 (#164)
| Benchmark | GPT-6.1 Sol | Mercury |
|---|---|---|
| DeepSWE | 75.2% | — |
| LMArena Coding | — | 1323 |
Agentic & Tool Use Not comparable
GPT-6.1 Sol: 34.3, Mercury: —
| Benchmark | GPT-6.1 Sol | Mercury |
|---|---|---|
| GDP.pdf | 32% | — |
Reasoning Not comparable
GPT-6.1 Sol: —, Mercury: 16.8 (#288)
| Benchmark | GPT-6.1 Sol | Mercury |
|---|---|---|
| Kagi LLM Benchmark | — | 21.6% |
| LMArena Hard Prompts | — | 1284 |
Multilingual Not comparable
GPT-6.1 Sol: —, Mercury: 41.7 (#201)
| Benchmark | GPT-6.1 Sol | Mercury |
|---|---|---|
| LMArena Non-English | — | 1259 |
Instruction Following Not comparable
GPT-6.1 Sol: —, Mercury: 65.3 (#220)
| Benchmark | GPT-6.1 Sol | Mercury |
|---|---|---|
| LMArena Instruction Following | — | 1238 |
Long Context Not comparable
GPT-6.1 Sol: —, Mercury: 38.3 (#193)
| Benchmark | GPT-6.1 Sol | Mercury |
|---|---|---|
| LMArena Longer Query | — | 1264 |
Writing & Preference Not comparable
GPT-6.1 Sol: —, Mercury: 46.2 (#216)
| Benchmark | GPT-6.1 Sol | Mercury |
|---|---|---|
| LMArena Text | — | 1282 |
| LMArena Creative Writing | — | 1186 |
| LMArena Multi-Turn | — | 1283 |
Frequently asked questions
Is GPT-6.1 Sol better than Mercury?
Mercury has enough public results to be ranked (#192); GPT-6.1 Sol does not yet, so treat this comparison as directional.
Is GPT-6.1 Sol or Mercury better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 51.4 versus 38.1 in the Noometry coding category.
How many benchmarks do GPT-6.1 Sol and Mercury share?
0 benchmarks have published results for both models. GPT-6.1 Sol has 2 scored results on Noometry and Mercury has 9.