ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GLM-4.6vsGPT-5.1

GLM-4.6 and GPT-5.1 split their 2 shared benchmarks evenly. GLM-4.6 is 4x cheaper per token. GPT-5.1 has the larger context window (400K tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
1 – 1
even split
Cheaper per token
GLM-4.6
4x cheaper, input + output
Larger context
GPT-5.1
400K tokens
Provider uptime (30d)
— · 94.2446%
Z.ai · OpenAI
text
Context
200K
Max out
131K
Input /1M
$0.6
Output /1M
$2.2
Cached /1M
$0.11
Scores
2 · 2 core
GPT-5.1
OpenAI · released 2025-11-13
textvision
Context
400K
Max out
128K
Input /1M
$1.25
Output /1M
$10
Cached /1M
$0.125
Scores
6 · 6 core
Quality

Benchmark matrix

BenchmarkGLM-4.6GPT-5.1ΔEdge
Reported by both · 2
AIME 202591.7% matharena94.2% matharena-2.5 ptGPT-5.1
LMArena Elo1440.5 1422.6 +17.9GLM-4.6
Only GLM-4.6 reports · 0
GLM-4.6 reports nothing GPT-5.1 does not.
Only GPT-5.1 reports · 4
GPQA Diamondnot reported87.6% epoch
OTIS Mock AIME 2024-2025 (Epoch AI run)not reported88.6% epoch
SimpleQA Verifiednot reported48% epoch
SWE-bench Verified (Epoch AI run)not reported68% epoch
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is GLM-4.6 minus GPT-5.1 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecGLM-4.6GPT-5.1Edge
Context window200K tokens400K tokensGPT-5.1
Max output131K tokens128K tokensGLM-4.6
Input price / 1M$0.6 $1.25 GLM-4.6
Output price / 1M$2.2 $10 GLM-4.6
Cached input / 1M$0.11 $0.125 GLM-4.6
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$2.8$11.25GLM-4.6
Modalitiestexttext · visionGPT-5.1
Released2025-11-13
Cited benchmark scores26
Reliability

Provider status

All providers
Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run GLM-4.6 and GPT-5.1 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.