# Gemini 2.5 Pro vs GPT-OSS 120B

> Side-by-side benchmark comparison for Gemini 2.5 Pro and GPT-OSS 120B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gemini-2-5-pro-vs-gpt-oss-120b
- Last updated: October 17, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Pick Gemini 2.5 Pro if you want the stronger benchmark profile. GPT-OSS 120B only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Gemini 2.5 Pro leads overall 49.14 to 37.32.
- The clearest category separation is in instruction following, where the averages are 57.8 for Gemini 2.5 Pro and 84.3 for GPT-OSS 120B.
- The biggest single benchmark swing is Gert Labs in Agentic, with scores of 42.01% and 29.61%.
- GPT-OSS 120B is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Gemini 2.5 Pro also has the larger context window at 1M.

## Model Snapshot

| Property | Gemini 2.5 Pro | GPT-OSS 120B |
|----------|----------|----------|
| Creator | Google | OpenAI |
| Type | Proprietary | Open Weight |
| Reasoning | Non-Reasoning | Non-Reasoning |
| Context | 1M | 128K |
| Overall Score | 49.14 | 37.32 |
| Benchmarks Covered | 9 | 8 |
| Pricing (input/output) | $1.25 / $10.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Directional only
- Gemini 2.5 Pro public-lane score: 25.7 (Estimated · #102/128)
- GPT-OSS 120B public-lane score: 19.5 (Estimated · #110/128)

| Benchmark | Gemini 2.5 Pro | GPT-OSS 120B | Winner |
|-----------|-----------|-----------|--------|
| Gert Labs | 42.01% | 29.61% | Gemini 2.5 Pro |

### Coding

- Winner: Directional only
- Gemini 2.5 Pro public-lane score: 22.3 (Supported · #115/150)
- GPT-OSS 120B public-lane score: 23 (Estimated · #111/150)

| Benchmark | Gemini 2.5 Pro | GPT-OSS 120B | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 63.8% | 62.4% | Gemini 2.5 Pro |
| Vibe Code Bench | 0.40% | Coming soon | Coming soon |
| SWE-bench (Vals) | 54.4% | Coming soon | Coming soon |
| React Native Evals | Coming soon | 71.6% | Coming soon |

### Reasoning

- Winner: Not comparable
- Gemini 2.5 Pro public-lane score: 73.3 (Unranked · 2 rankable rows)
- GPT-OSS 120B public-lane score: 61.6 (Unranked · 2 rankable rows)

### Multimodal & Grounded

- Winner: Not comparable
- Gemini 2.5 Pro public-lane score: 74.8 (Unranked · 1 rankable row)
- GPT-OSS 120B public-lane score: Coming soon

### Knowledge

- Winner: Gemini 2.5 Pro
- Gemini 2.5 Pro public-lane score: 45.6 (Supported · #96/184)
- GPT-OSS 120B public-lane score: 38.6 (Supported · #122/184)

| Benchmark | Gemini 2.5 Pro | GPT-OSS 120B | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 83% | 80.1% | Gemini 2.5 Pro |
| HLE | 18.8% | 14.9% | Gemini 2.5 Pro |
| MMLU | Coming soon | 90% | Coming soon |

### Instruction Following

- Winner: Directional only
- Gemini 2.5 Pro public-lane score: 57.8 (#83/148)
- GPT-OSS 120B public-lane score: 84.3 (#50/148)

### Mathematics

- Winner: Not comparable
- Gemini 2.5 Pro public-lane score: 36.9 (Unranked · 3 rankable rows)
- GPT-OSS 120B public-lane score: Coming soon

| Benchmark | Gemini 2.5 Pro | GPT-OSS 120B | Winner |
|-----------|-----------|-----------|--------|
| AIME 2024 | 92% | 95.8% | GPT-OSS 120B |
| FrontierMath v2 (Tiers 1-3) | 24.561% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 0.000% | Coming soon | Coming soon |
| AIME 2025 | Coming soon | 92.5% | Coming soon |

## FAQ

### Which is better overall, Gemini 2.5 Pro or GPT-OSS 120B?

Gemini 2.5 Pro is ahead overall on BenchLM right now.

### Where is the biggest gap between Gemini 2.5 Pro and GPT-OSS 120B?

The widest category gap is in instruction following, where the averages are 57.8 for Gemini 2.5 Pro and 84.3 for GPT-OSS 120B.

### How many benchmarks does Gemini 2.5 Pro cover on BenchLM?

Gemini 2.5 Pro currently has 9 sourced benchmark scores on BenchLM.

### How many benchmarks does GPT-OSS 120B cover on BenchLM?

GPT-OSS 120B currently has 8 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Gemini 2.5 Pro vs GPT-OSS 20B](/compare/gemini-2-5-pro-vs-gpt-oss-20b)
- [GPT-OSS 120B vs GPT-OSS 20B](/compare/gpt-oss-120b-vs-gpt-oss-20b)
- [Gemini 2.5 Pro vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-gemini-2-5-pro)
- [GPT-OSS 120B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-gpt-oss-120b)

## Explore More

- [Gemini 2.5 Pro profile](/models/gemini-2-5-pro)
- [GPT-OSS 120B profile](/models/gpt-oss-120b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)