Model comparison
GPT-6 Sol vs Mercury 2.5
GPT-6 Sol is the stronger model overall, scoring 61.8 to 33.5 on the Noometry Index. Mercury 2.5 costs 59× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Summary
- They share 4 benchmarks with published results for both. GPT-6 Sol scores higher in 3 categories and Mercury 2.5 in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 23.3.
- The biggest single-benchmark swing is ProofBench: 83% for GPT-6 Sol and 3% for Mercury 2.5.
- Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 260K.
Side by side
| GPT-6 Sol | Mercury 2.5 | |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 61.8 | 33.5 |
| Released | 2026-09-22 | 2026-09-08 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 260K |
| Max output | 128K | 66K |
| Input $ / M tokens | $2 | $0.04 |
| Output $ / M tokens | $10 | $0.15 |
| Results tracked | 45 | 4 |
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 2.5: 39.5 (#156)
| Benchmark | GPT-6 Sol | Mercury 2.5 |
|---|---|---|
| SciCode | 57.6% | 38.5% |
| ALE-Bench | 2,462 | 301.65 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| LMArena WebDev | 1688 | — |
| LMArena Coding | 1447 | — |
Agentic & Tool Use Not comparable
GPT-6 Sol: 37.2 (#36), Mercury 2.5: —
| Benchmark | GPT-6 Sol | Mercury 2.5 |
|---|---|---|
| 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 2.5: 22.4 (#193)
| Benchmark | GPT-6 Sol | Mercury 2.5 |
|---|---|---|
| CritPt | 30.9% | 0% |
| ARC-AGI-2 | 89.6% | — |
| NYT Connections (extended) | 90.1% | — |
| ARC-AGI-1 | 95.5% | — |
| EBR-Bench | 53.3% | — |
| LMArena Hard Prompts | 1418 | — |
| Mystery Game Puzzles | 56% | — |
| DTBench | 97.3% | — |
| LMCA | 59.1% | — |
| Epoch Capabilities Index | 162.72 | — |
Math GPT-6 Sol leads
GPT-6 Sol: 87.2 (#7), Mercury 2.5: 23.3 (#272)
| Benchmark | GPT-6 Sol | Mercury 2.5 |
|---|---|---|
| ProofBench | 83% | 3% |
| FrontierMath (Tiers 1-3) | 89.8% | — |
| FrontierMath Tier 4 | 90% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| LMArena Math | 1402 | — |
Knowledge Not comparable
GPT-6 Sol: 64.8 (#15), Mercury 2.5: —
| Benchmark | GPT-6 Sol | Mercury 2.5 |
|---|---|---|
| GPQA Diamond | 94.3% | — |
| SimpleQA Verified | 60.7% | — |
| Vectara Hallucination Rate | 6.5% | — |
| LMArena Expert | 1439 | — |
Multimodal Not comparable
GPT-6 Sol: 47.6 (#10), Mercury 2.5: —
| Benchmark | GPT-6 Sol | Mercury 2.5 |
|---|---|---|
| LMArena Vision | 1245 | — |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |
Multilingual Not comparable
GPT-6 Sol: 50.5 (#118), Mercury 2.5: —
| Benchmark | GPT-6 Sol | Mercury 2.5 |
|---|---|---|
| LMArena Non-English | 1385 | — |
| LMArena Chinese | 1405 | — |
| LMArena French | 1410 | — |
| LMArena German | 1390 | — |
| LMArena Japanese | 1385 | — |
| LMArena Korean | 1341 | — |
| LMArena Russian | 1401 | — |
| LMArena Spanish | 1384 | — |
Instruction Following Not comparable
GPT-6 Sol: 74.5 (#94), Mercury 2.5: —
| Benchmark | GPT-6 Sol | Mercury 2.5 |
|---|---|---|
| LMArena Instruction Following | 1412 | — |
Long Context Not comparable
GPT-6 Sol: 43.1 (#108), Mercury 2.5: —
| Benchmark | GPT-6 Sol | Mercury 2.5 |
|---|---|---|
| LMArena Longer Query | 1411 | — |
Writing & Preference Not comparable
GPT-6 Sol: 71.9 (#18), Mercury 2.5: —
| Benchmark | GPT-6 Sol | Mercury 2.5 |
|---|---|---|
| LMArena Text | 1395 | — |
| LMArena Creative Writing | 1378 | — |
| EQ-Bench Creative Writing | 2125 | — |
| LMArena Multi-Turn | 1412 | — |
Frequently asked questions
Is GPT-6 Sol better than Mercury 2.5?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 33.5 on the Noometry Index. Mercury 2.5 costs 59× 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 2.5?
Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is GPT-6 Sol or Mercury 2.5 better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 39.5 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 260K.
How many benchmarks do GPT-6 Sol and Mercury 2.5 share?
4 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Mercury 2.5 has 4.