ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GLM-4.7vsGLM-5

GLM-5 leads 2 of 3 shared benchmarks. GLM-4.7 is 1.5x cheaper per token. Both offer a 200K-token context window.

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

Shared benchmarks
1 – 2
GLM-5 leads
Cheaper per token
GLM-4.7
1.5x cheaper, input + output
Larger context
Tie
both 200K tokens
Provider uptime (30d)
Z.ai
GLM-4.7
Z.ai · released 2025-12-22
text
Context
200K
Max out
131K
Input /1M
$0.6
Output /1M
$2.2
Cached /1M
$0.11
Scores
4 · 4 core
GLM-5
Z.ai
text
Context
200K
Max out
131K
Input /1M
$1
Output /1M
$3.2
Cached /1M
$0.2
Scores
8 · 7 core
Quality

Benchmark matrix

BenchmarkGLM-4.7GLM-5ΔEdge
Reported by both · 3
GPQA Diamond83.3% epoch87.8% epoch-4.5 ptGLM-5
LMArena Elo1435.9 1446.3 -10.4GLM-5
OTIS Mock AIME 2024-2025 (Epoch AI run)83.3% epoch80% epoch+3.3 ptGLM-4.7
Only GLM-4.7 reports · 1
SimpleQA Verified32.2% epochnot reported
Only GLM-5 reports · 5
SWE-bench Verifiednot reported77.8%
AIME 2025not reported96.7% matharena
AIME 2026not reported96.7% matharena
SWE-bench Verified (Epoch AI run)not reported72.1% epoch
Terminal-Bench 2.0not reported56.2%
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-4.7 minus GLM-5 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-4.7GLM-5Edge
Context window200K tokens200K tokensTie
Max output131K tokens131K tokensTie
Input price / 1M$0.6 $1 GLM-4.7
Output price / 1M$2.2 $3.2 GLM-4.7
Cached input / 1M$0.11 $0.2 GLM-4.7
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$2.8$4.2GLM-4.7
ModalitiestexttextTie
Released2025-12-22
Cited benchmark scores48
Reliability

Z.ai status

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

Public benchmarks are a starting point. Run GLM-4.7 and GLM-5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.