Model comparison
GPT-6 Sol vs Mercury 2
GPT-6 Sol is the stronger model overall, scoring 61.8 to 39.1 on the Noometry Index. Mercury 2 costs 11× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. GPT-6 Sol scores higher in 7 categories and Mercury 2 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 23.8.
- The biggest single-benchmark swing is CritPt: 30.9% for GPT-6 Sol and 0.8% for Mercury 2.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 128K.
Side by side
| GPT-6 Sol | Mercury 2 | |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 61.8 | 39.1 |
| Released | 2026-09-22 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 128K |
| Max output | 128K | 50K |
| Input $ / M tokens | $2 | $0.25 |
| Output $ / M tokens | $10 | $0.75 |
| Results tracked | 45 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GPT-6 Sol: 60.1 (#11), Mercury 2: 33.5 (#255)
| Benchmark | GPT-6 Sol | Mercury 2 |
|---|---|---|
| LMArena WebDev | 1688 | 1171 |
| SciCode | 57.6% | 38.7% |
| LMArena Coding | 1447 | 1391 |
| ALE-Bench | 2,462 | 785.58 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| WeirdML | — | 43.2% |
Agentic & Tool Use Not comparable
GPT-6 Sol: 37.2 (#36), Mercury 2: —
| Benchmark | GPT-6 Sol | Mercury 2 |
|---|---|---|
| APEX-Agents | 54.3% | — |
| GDP.pdf | 26.4% | — |
| Vending-Bench 2 | 14,428 | — |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 74.0 (#9), Mercury 2: 23.8 (#170)
| Benchmark | GPT-6 Sol | Mercury 2 |
|---|---|---|
| CritPt | 30.9% | 0.8% |
| LMArena Hard Prompts | 1418 | 1362 |
| ARC-AGI-2 | 89.6% | — |
| NYT Connections (extended) | 90.1% | — |
| ARC-AGI-1 | 95.5% | — |
| EBR-Bench | 53.3% | — |
| Mystery Game Puzzles | 56% | — |
| DTBench | 97.3% | — |
| LMCA | 59.1% | — |
| Epoch Capabilities Index | 162.72 | — |
Math Not comparable
GPT-6 Sol: 87.2 (#7), Mercury 2: —
| Benchmark | GPT-6 Sol | Mercury 2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 89.8% | — |
| FrontierMath Tier 4 | 90% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 83% | — |
| LMArena Math | 1402 | — |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 64.8 (#15), Mercury 2: 36.2 (#172)
| Benchmark | GPT-6 Sol | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | 6.5% | 12.3% |
| LMArena Expert | 1439 | 1358 |
| GPQA Diamond | 94.3% | — |
| SimpleQA Verified | 60.7% | — |
Multimodal Not comparable
GPT-6 Sol: 47.6 (#10), Mercury 2: —
| Benchmark | GPT-6 Sol | Mercury 2 |
|---|---|---|
| LMArena Vision | 1245 | — |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |
Multilingual GPT-6 Sol leads
GPT-6 Sol: 50.5 (#118), Mercury 2: 46.6 (#157)
| Benchmark | GPT-6 Sol | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1385 | 1331 |
| LMArena Chinese | 1405 | 1417 |
| LMArena Russian | 1401 | 1304 |
| LMArena French | 1410 | — |
| LMArena German | 1390 | — |
| LMArena Japanese | 1385 | — |
| LMArena Korean | 1341 | — |
| LMArena Spanish | 1384 | — |
Instruction Following GPT-6 Sol leads
GPT-6 Sol: 74.5 (#94), Mercury 2: 70.2 (#165)
| Benchmark | GPT-6 Sol | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1412 | 1329 |
Long Context GPT-6 Sol leads
GPT-6 Sol: 43.1 (#108), Mercury 2: 40.5 (#154)
| Benchmark | GPT-6 Sol | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1411 | 1330 |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 71.9 (#18), Mercury 2: 53.8 (#155)
| Benchmark | GPT-6 Sol | Mercury 2 |
|---|---|---|
| LMArena Text | 1395 | 1355 |
| LMArena Creative Writing | 1378 | 1289 |
| LMArena Multi-Turn | 1412 | 1358 |
| EQ-Bench Creative Writing | 2125 | — |
Frequently asked questions
Is GPT-6 Sol better than Mercury 2?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 39.1 on the Noometry Index. Mercury 2 costs 11× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-6 Sol or Mercury 2?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is GPT-6 Sol or Mercury 2 better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 128K.
How many benchmarks do GPT-6 Sol and Mercury 2 share?
16 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Mercury 2 has 17.