Compare / gpt-oss-20b vs GLM-4.6V

gpt-oss-20b vs GLM-4.6V

Which is cheaper, which is more capable, and which does better at each kind of work, from 16 results on 3 sources that measured both models.

OpenAIgpt-oss-20b Released 5 Aug 2025 · $0.030 in · $0.14 out
Z.aiGLM-4.6V Released 8 Dec 2025 · $0.30 in · $0.90 out
gpt-oss-20b wins 3GLM-4.6V wins 13

Of the 16 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee). See also OpenAI vs Z.ai, every model from both labs.

gpt-oss-20b or GLM-4.6V? The short answer

They score about the same, so pick gpt-oss-20b: it costs 7.8 times less per token.

  • gpt-oss-20b is cheaper: $0.058 against $0.45 per million tokens, 7.8 times less.
  • GLM-4.6V scores higher on the Artificial Analysis Intelligence Index: 11.2 against 10.0.
  • GLM-4.6V is newer: released 8 Dec 2025, against 5 Aug 2025 for gpt-oss-20b.
  • On third-party benchmarks, on the results both models have: GLM-4.6V does better for reasoning and knowledge and writing.

Head to head

10.0
Intelligence Index
11.2
$0.058
Price per million tokens, blendedlower is better
$0.45
131,072
Context window, tokens
131,072

Every fact side by side

gpt-oss-20bGLM-4.6V
Price per million tokens$0.030 in · $0.14 out$0.30 in · $0.90 out
Blended (3 in : 1 out)$0.058$0.45
Cheapest host, blended$0.022 (PrimeIntellect, FP4)$0.45 (Novita, BF16)
Intelligence Index10.011.2
Spring Prompt overall––
Output speed, tokens a second277–
Context window131,072 tokens131,072 tokens
Released5 Aug 20258 Dec 2025 (newer)
WeightsOpenOpen
Developer based inthe USChina

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 130 of 159 not measured
Reasoning and knowledgeHard questions across science, maths and general knowledge 132 of 187 130 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 155 of 169 114 of 169
Sticking to the factsSummarising without inventing things, and factual answers not measured 130 of 139

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

Measuregpt-oss-20bGLM-4.6V
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 237 · 164 of 387 measured 1,318 1,379
Business, management and finance · TextArena rating, higher is better 213 · 165 of 380 measured 1,323 1,370
Creative writing · TextArena rating, higher is better 275 · 153 of 385 measured 1,240 1,351
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 176 · 166 of 249 measured 10.0low reasoning 11.2thinking reasoning
GPQA Diamond% of questions, higher is better 159 · 152 of 232 measured 68.8%high reasoning 71.9%thinking reasoning
Humanity's Last Exam% of questions, higher is better 153 · 167 of 250 measured 11.0%high reasoning 9.6%thinking reasoning
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 182 · 111 of 230 measured 24.6low reasoning 39.7thinking reasoning
Requested-length error · UGI% off the requested word count, lower is better 221 · 180 of 230 measured 98.0%low reasoning 35.0%thinking reasoning
Style adherence · UGIscore from 0 to 1, higher is better 187 · 22 of 230 measured 0.31medium reasoning 0.39no reasoning
Show all 16 results (7 more)
Measuregpt-oss-20bGLM-4.6V
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 220 · 164 of 338 measured 1,314 1,394
Instruction following · TextArena rating, higher is better 257 · 163 of 387 measured 1,281 1,367
Writing, literature and language · TextArena rating, higher is better 261 · 160 of 386 measured 1,275 1,357
Artificial Analysis reported by Artificial Analysis · 4 results
IFBench% of instructions, higher is better 69 · 181 of 195 measured 65.1%high reasoning 30.1%thinking reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 184 · 166 of 241 measured 34.7%high reasoning 48.7%thinking reasoning
Terminal-Bench Hard% of tasks, higher is better 127 · 114 of 190 measured 10.6%high reasoning 14.4%thinking reasoning
τ²-bench telecom% of tasks, higher is better 96 · 130 of 193 measured 60.2%high reasoning 31.6%thinking reasoning

Quick answers

Is gpt-oss-20b better than GLM-4.6V?

They score about the same, so pick gpt-oss-20b: it costs 7.8 times less per token.

Which is cheaper, gpt-oss-20b or GLM-4.6V?

gpt-oss-20b is cheaper: $0.058 against $0.45 per million tokens, 7.8 times less.

Which is better for reasoning and knowledge, gpt-oss-20b or GLM-4.6V?

GLM-4.6V ranks 130 of 187 models on sale for hard questions across science, maths and general knowledge, against 132 for gpt-oss-20b.

Which is better for writing, gpt-oss-20b or GLM-4.6V?

GLM-4.6V ranks 114 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 155 for gpt-oss-20b.

Run gpt-oss-20b and GLM-4.6V on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.