Model comparison
GPT-5.6 Terra vs Mercury 2
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 39.1 on the Noometry Index. Mercury 2 costs 12× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. GPT-5.6 Terra 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-5.6 Terra leads 60.7 to 23.8.
- The biggest single-benchmark swing is WeirdML: 78.3% for GPT-5.6 Terra and 43.2% for Mercury 2.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2 / $12 for GPT-5.6 Terra.
- GPT-5.6 Terra accepts more context: 1.05M tokens versus 128K.
Side by side
| GPT-5.6 Terra | Mercury 2 | |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 59.2 | 39.1 |
| Released | 2026-07-09 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 128K |
| Max output | 128K | 50K |
| Input $ / M tokens | $2 | $0.25 |
| Output $ / M tokens | $12 | $0.75 |
| Results tracked | 52 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Terra leads
GPT-5.6 Terra: 57.7 (#19), Mercury 2: 33.5 (#255)
| Benchmark | GPT-5.6 Terra | Mercury 2 |
|---|---|---|
| LMArena WebDev | 1522 | 1171 |
| SciCode | 55% | 38.7% |
| WeirdML | 78.3% | 43.2% |
| LMArena Coding | 1484 | 1391 |
| ALE-Bench | 1,951 | 785.58 |
| DeepSWE | 69.6% | — |
| FrontierCode | 41.3% | — |
| CursorBench | 41.3% | — |
Agentic & Tool Use Not comparable
GPT-5.6 Terra: 40.1 (#25), Mercury 2: —
| Benchmark | GPT-5.6 Terra | Mercury 2 |
|---|---|---|
| APEX-Agents | 58.2% | — |
| BALROG | 53.2% | — |
| GDP.pdf | 24.7% | — |
| Vending-Bench 2 | 7,343 | — |
Reasoning GPT-5.6 Terra leads
GPT-5.6 Terra: 60.7 (#21), Mercury 2: 23.8 (#170)
| Benchmark | GPT-5.6 Terra | Mercury 2 |
|---|---|---|
| CritPt | 30% | 0.8% |
| LMArena Hard Prompts | 1468 | 1362 |
| ARC-AGI-2 | 83.9% | — |
| SimpleBench | 48.9% | — |
| Kagi LLM Benchmark | 51.3% | — |
| NYT Connections (extended) | 78.4% | — |
| ARC-AGI-1 | 96.5% | — |
| Chess Puzzles | 54% | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 93.3% | — |
| LMCA | 55% | — |
| Surface Evolver Bench | 83.8% | — |
| Epoch Capabilities Index | 159.62 | — |
Math Not comparable
GPT-5.6 Terra: 81.6 (#12), Mercury 2: —
| Benchmark | GPT-5.6 Terra | Mercury 2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 86% | — |
| FrontierMath Tier 4 | 70.7% | — |
| OTIS Mock AIME 2024-2025 | 99.7% | — |
| ProofBench | 74% | — |
| LMArena Math | 1466 | — |
Knowledge GPT-5.6 Terra leads
GPT-5.6 Terra: 61.2 (#30), Mercury 2: 36.2 (#172)
| Benchmark | GPT-5.6 Terra | Mercury 2 |
|---|---|---|
| LMArena Expert | 1492 | 1358 |
| GPQA Diamond | 93.3% | — |
| SimpleQA Verified | 43.2% | — |
| Vectara Hallucination Rate | — | 12.3% |
Multimodal Not comparable
GPT-5.6 Terra: 47.3 (#11), Mercury 2: —
| Benchmark | GPT-5.6 Terra | Mercury 2 |
|---|---|---|
| LMArena Vision | 1271 | — |
| Blueprint-Bench 2 | 30.8% | — |
| Furniture Assembly | 54.2% | — |
| LMArena Document | 1472 | — |
Multilingual GPT-5.6 Terra leads
GPT-5.6 Terra: 54.4 (#44), Mercury 2: 46.6 (#157)
| Benchmark | GPT-5.6 Terra | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1439 | 1331 |
| LMArena Chinese | 1513 | 1417 |
| LMArena Russian | 1450 | 1304 |
| LMArena French | 1471 | — |
| LMArena German | 1460 | — |
| LMArena Japanese | 1457 | — |
| LMArena Korean | 1425 | — |
| LMArena Spanish | 1448 | — |
Instruction Following GPT-5.6 Terra leads
GPT-5.6 Terra: 76.4 (#40), Mercury 2: 70.2 (#165)
| Benchmark | GPT-5.6 Terra | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1454 | 1329 |
Long Context GPT-5.6 Terra leads
GPT-5.6 Terra: 44.4 (#68), Mercury 2: 40.5 (#154)
| Benchmark | GPT-5.6 Terra | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1451 | 1330 |
Writing & Preference GPT-5.6 Terra leads
GPT-5.6 Terra: 70.2 (#23), Mercury 2: 53.8 (#155)
| Benchmark | GPT-5.6 Terra | Mercury 2 |
|---|---|---|
| LMArena Text | 1447 | 1355 |
| LMArena Creative Writing | 1410 | 1289 |
| LMArena Multi-Turn | 1449 | 1358 |
| EQ-Bench Creative Writing | 1855 | — |
| EQ-Bench 4 | 1234 | — |
Frequently asked questions
Is GPT-5.6 Terra better than Mercury 2?
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 39.1 on the Noometry Index. Mercury 2 costs 12× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Which is cheaper, GPT-5.6 Terra or Mercury 2?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GPT-5.6 Terra lists at $2 and $12.
Is GPT-5.6 Terra or Mercury 2 better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.7 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Terra does, with 1.05M tokens against 128K.
How many benchmarks do GPT-5.6 Terra and Mercury 2 share?
16 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and Mercury 2 has 17.