Model comparison
gpt-oss-120b vs Mercury 2
Mercury 2 is the stronger model overall, scoring 39.1 to 36.3 on the Noometry Index. gpt-oss-120b costs 5.3× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. gpt-oss-120b scores higher in 2 categories and Mercury 2 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where Mercury 2 leads 40.5 to 31.4.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
- gpt-oss-120b accepts more context: 131K tokens versus 128K.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-120b | Mercury 2 | |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 36.3 | 39.1 |
| Released | 2025-08-05 | 2026-02-20 |
| Weights | Open | Proprietary |
| Context window | 131K | 128K |
| Max output | 41K | 50K |
| Input $ / M tokens | $0.037 | $0.25 |
| Output $ / M tokens | $0.17 | $0.75 |
| Results tracked | 48 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
gpt-oss-120b: 33.5 (#256), Mercury 2: 33.5 (#255)
| Benchmark | gpt-oss-120b | Mercury 2 |
|---|---|---|
| SciCode | 36% | 38.7% |
| WeirdML | 48.2% | 43.2% |
| LMArena Coding | 1380 | 1391 |
| ALE-Bench | 575.62 | 785.58 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| LMArena WebDev | — | 1171 |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Not comparable
gpt-oss-120b: 12.2 (#153), Mercury 2: —
| Benchmark | gpt-oss-120b | Mercury 2 |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning Mercury 2 leads
gpt-oss-120b: 20.0 (#245), Mercury 2: 23.8 (#170)
| Benchmark | gpt-oss-120b | Mercury 2 |
|---|---|---|
| CritPt | 1.1% | 0.8% |
| LMArena Hard Prompts | 1364 | 1362 |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| Epoch Capabilities Index | 139.93 | — |
Math Not comparable
gpt-oss-120b: 52.5 (#50), Mercury 2: —
| Benchmark | gpt-oss-120b | Mercury 2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| Omni-MATH | 68.8% | — |
| LMArena Math | 1389 | — |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.4 (#96), Mercury 2: 36.2 (#172)
| Benchmark | gpt-oss-120b | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | 14.2% | 12.3% |
| LMArena Expert | 1356 | 1358 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| GPQA (HELM) | 68.4% | — |
Multilingual gpt-oss-120b leads
gpt-oss-120b: 48.0 (#147), Mercury 2: 46.6 (#157)
| Benchmark | gpt-oss-120b | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1351 | 1331 |
| LMArena Chinese | 1385 | 1417 |
| LMArena Russian | 1343 | 1304 |
| LMArena French | 1369 | — |
| LMArena German | 1353 | — |
| LMArena Japanese | 1331 | — |
| LMArena Korean | 1282 | — |
| LMArena Spanish | 1389 | — |
Instruction Following Too close to call
gpt-oss-120b: 69.3 (#173), Mercury 2: 70.2 (#165)
| Benchmark | gpt-oss-120b | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1318 | 1329 |
| IFEval | 83.6% | — |
Long Context Mercury 2 leads
gpt-oss-120b: 31.4 (#278), Mercury 2: 40.5 (#154)
| Benchmark | gpt-oss-120b | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1319 | 1330 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Mercury 2 leads
gpt-oss-120b: 46.5 (#217), Mercury 2: 53.8 (#155)
| Benchmark | gpt-oss-120b | Mercury 2 |
|---|---|---|
| LMArena Text | 1365 | 1355 |
| LMArena Creative Writing | 1275 | 1289 |
| LMArena Multi-Turn | 1340 | 1358 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Mercury 2?
Mercury 2 is the stronger model overall, scoring 39.1 to 36.3 on the Noometry Index. gpt-oss-120b costs 5.3× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-120b or Mercury 2?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Mercury 2 lists at $0.25 and $0.75.
Is gpt-oss-120b or Mercury 2 better for coding?
They score almost the same on coding (33.5 vs 33.5); test both on your own repository before choosing.
Which has the bigger context window?
gpt-oss-120b does, with 131K tokens against 128K.
How many benchmarks do gpt-oss-120b and Mercury 2 share?
16 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Mercury 2 has 17.