GPT-OSS 20B vs MiniMax M2.7

Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.

MiniMax M2.7 is clearly ahead on the aggregate, 57 to 32. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

MiniMax M2.7's sharpest advantage is in coding, where it averages 56.2 against 14.4. The single biggest benchmark swing on the page is SWE-bench Pro, 18% to 56.2%.

MiniMax M2.7 is also the more expensive model on tokens at $0.30 input / $1.20 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for GPT-OSS 20B. That is roughly Infinityx on output cost alone. MiniMax M2.7 gives you the larger context window at 200K, compared with 128K for GPT-OSS 20B.

Quick Verdict

Pick MiniMax M2.7 if you want the stronger benchmark profile. GPT-OSS 20B only becomes the better choice if you want the cheaper token bill.

Agentic

MiniMax M2.7

GPT-OSS 20B

35.4

MiniMax M2.7

57

35%
Terminal-Bench 2.0
57%
42%
BrowseComp
Coming soon
31%
OSWorld-Verified
Coming soon
Coming soon
Toolathlon
46.3%
Coming soon
MLE-Bench Lite
66.6%
Coming soon
MM-ClawBench
62.7%

Coding

MiniMax M2.7

GPT-OSS 20B

14.4

MiniMax M2.7

56.2

23%
HumanEval
Coming soon
14%
SWE-bench Verified
Coming soon
11%
LiveCodeBench
Coming soon
18%
SWE-bench Pro
56.2%
Coming soon
SWE Multilingual
76.5%
Coming soon
Multi-SWE Bench
52.7%
Coming soon
VIBE-Pro
55.6%
Coming soon
NL2Repo
39.8%

Multimodal & Grounded

Coming soon

Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.

31%
MMMU-Pro
Coming soon
42%
OfficeQA Pro
Coming soon
Coming soon
GDPval-AA
1495

Reasoning

Coming soon

Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.

27%
MuSR
Coming soon
62%
BBH
Coming soon
48%
LongBench v2
Coming soon

Knowledge

Coming soon

Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.

85.3%
MMLU
Coming soon
30%
GPQA
Coming soon
28%
SuperGPQA
Coming soon
1%
HLE
Coming soon
34%
FrontierScience
Coming soon
29%
SimpleQA
Coming soon
Coming soon
Artificial Analysis
50

Instruction Following

Coming soon

Benchmark data for this category is coming soon.

Multilingual

Coming soon

Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.

61%
MGSM
Coming soon

Mathematics

Coming soon

Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.

31%
AIME 2023
Coming soon
33%
AIME 2024
Coming soon
32%
AIME 2025
Coming soon
27%
HMMT Feb 2023
Coming soon
29%
HMMT Feb 2024
Coming soon
28%
HMMT Feb 2025
Coming soon
30%
BRUMO 2025
Coming soon

Frequently Asked Questions

Which is better, GPT-OSS 20B or MiniMax M2.7?

MiniMax M2.7 is ahead overall, 57 to 32. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 18% and 56.2%.

Which is better for coding, GPT-OSS 20B or MiniMax M2.7?

MiniMax M2.7 has the edge for coding in this comparison, averaging 56.2 versus 14.4. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GPT-OSS 20B or MiniMax M2.7?

MiniMax M2.7 has the edge for agentic tasks in this comparison, averaging 57 versus 35.4. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Last updated: March 18, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.