gpt-oss-120b vs Perceptron Mk1.5: which should you choose in 2026?
gpt-oss-120b (by OpenAI) and Perceptron Mk1.5 (by Perceptron) are compared below. Here is how they stack up on benchmarks, price, and capabilities, and which one to pick in 2026.
There are not enough shared, protocol-compatible benchmark results to declare a performance leader.
gpt-oss-120b is about 6.9× cheaper on a blended 3:1 input/output basis ($0.07025 vs $0.4875 per 1M tokens).
gpt-oss-120b has the larger context window (131,072 tokens vs 36,864 tokens).
Choose gpt-oss-120b if…
- • lower blended API cost matters for your workload
- • you work with longer documents, transcripts, or codebases
Choose Perceptron Mk1.5 if…
- • you need image inputs
The benchmark count includes only results measured with a matching benchmark version and protocol. Arena scores are shown separately. Missing, preliminary, and incompatible data is not treated as a controlled win. Published point-score comparisons are labeled separately when protocol details are incomplete. For text-output models, the verdict also compares token pricing and context windows.
Performance benchmarks
Every value links to its source. A dash means that no reviewed result is available for that exact model and protocol.
| Benchmark | gpt-oss-120b | Perceptron Mk1.5 |
|---|---|---|
A 657-task benchmark of multi-step work across simulated SaaS applications in six business domains. The Artificial Analysis protocol reports a guardrail-aware score and is distinct from both the public Zapier split and the unrelated dynamic AutoBench framework. Guardrail-aware score | — | — |
A benchmark of difficult, verifiable information-seeking questions designed to measure an agent's ability to locate hard-to-find facts through web browsing. Accuracy | — | — |
A verified computer-use benchmark in which multimodal agents operate desktop applications and are graded from the resulting environment state. Mean task reward | — | — |
A human-validated subset of real GitHub issues used to measure whether a coding agent can produce repository patches that resolve the associated tests. Resolved | 26.0% SWE-bench | — |
Version 2.1 of the benchmark for completing realistic tasks in terminal environments. Harness, resource limits, and attempt count are part of the protocol. Mean task success | — | — |
A dynamic LLM evaluation framework in which models generate questions, answer them, and participate in reciprocal peer assessment. AutoBench is distinct from Zapier's AutomationBench. Weighted peer-assessment score | — | — |
The highest-quality subset of Graduate-Level Google-Proof Q&A, designed to test expert-level scientific reasoning in biology, physics, and chemistry. Accuracy | — | — |
A 2,500-question expert-level benchmark spanning dozens of academic fields. Tool-assisted and no-tools results are separate protocols and must not be merged. Accuracy | — | — |
| Arena preference scores | ||
Human preference score | 1352 ±4 | — |
Benchmark sources
Reviewed evidence last updated 2026-08-09. Arena data last refreshed Oct 4, 2026.
Pricing, capabilities, and model facts
| Feature | gpt-oss-120b | Perceptron Mk1.5 |
|---|---|---|
| Context & model facts | ||
| Developer | OpenAI | Perceptron |
| API provider | OpenAI | Perceptron |
| Input context | 131,072 tokens | 36,864 tokens |
| Maximum output | 117,964 tokens | 8,192 tokens |
| Released | — | — |
| Added to Writingmate | Aug 5, 2025 | Sep 25, 2026 |
| License | Not available | Not available |
| Knowledge cutoff | 2024-06-30 | — |
| Capabilities | ||
| Inputs | Text | Text, Image, Video, Audio |
| Outputs | Text | Text |
| Provider endpoint accepts tool parameters | Yes | Yes |
| Reasoning | Yes | Yes |
| Vision | No | Yes |
| Image Generation | No | No |
| Video Generation | No | No |
| API pricing | ||
| Input (per 1M tokens) | $0.037 | $0.15 |
| Output (per 1M tokens) | $0.17 | $1.50 |
| Blended 3:1 input/output | $0.07025 | $0.4875 |
| API performance | ||
| p95 latency | Not measured | Not measured |
| Output throughput | Not measured | Not measured |
| Writingmate shows API performance only when both models have enough observations from the same measurement window, prompt profile, and provider. Third-party latency values are not copied into this table. | ||
Data sources
- Writingmate model catalog (pricing, limits, and availability)
Catalog data last updated Sep 25, 2026.
Why Pay for Multiple Subscriptions?
Comparing gpt-oss-120b from OpenAI with Perceptron Mk1.5 from Perceptron? Instead of managing separate API keys and subscriptions, get both with Writingmate.
| Plan | Price | gpt-oss-120b | Perceptron Mk1.5 | AI Images | AI Video |
|---|---|---|---|---|---|
Writingmate Pro Most popular | $20/mo | Included | Included | Nano Banana Pro, FLUX.2, DALL-E & more | VEO 3.1, Kling 3.0 |
Writingmate Ultimate Power users | $60/mo | Included | Included | Nano Banana Pro, FLUX.2, DALL-E & more | VEO 3.1, Kling 3.0 |
gpt-oss-120b vs Perceptron Mk1.5 FAQ
Which is better, gpt-oss-120b or Perceptron Mk1.5?
There are not enough shared, protocol-compatible benchmark results to declare a performance leader. gpt-oss-120b is about 6.9× cheaper on a blended 3:1 input/output basis ($0.07025 vs $0.4875 per 1M tokens). gpt-oss-120b has the larger context window (131,072 tokens vs 36,864 tokens).
Which model is cheaper to use through an API?
gpt-oss-120b is about 6.9× cheaper on a blended 3:1 input/output basis ($0.07025 vs $0.4875 per 1M tokens).
Which model supports more context?
gpt-oss-120b has the larger context window (131,072 tokens vs 36,864 tokens).
Can I switch between gpt-oss-120b and Perceptron Mk1.5?
Yes. Use the model selector on this page to open any current Writingmate model comparison. You can also run the same prompt with both models in Writingmate.
Related comparisons
More gpt-oss-120b comparisons
Ling 3.1 Flash
inclusionAI
Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.
Claude Sonnet 5.5
Anthropic
Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.
Jev Router
Typesafe
Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost.
Ember-1
Fireworks
Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3.
GLM 5.3 Prime
Z.AI
GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration.
Qwen3.8 Max Prime
Qwen
Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point.
More Perceptron Mk1.5 comparisons
Jev Router
Typesafe
Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost.
MiMo-V2.6-Pro-UltraSpeed
Xiaomi
MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro.
MiMo-V2.6-Flash
Xiaomi
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi.
MiMo-V2.6-Pro
Xiaomi
MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi.
Qwen3.8 Omni Flash
Qwen
Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding.
Gemini 3.8 Flash
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.