Skip to main content
BenchLM
Advertise

Model comparison

Claude Sonnet 4.6 vs GLM-5

Data verified

Head-to-head evidence from 25 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

65.07/100
Margin
1.0pts
winning →
GLM-5
Z.AI
66.06/100
2 category wins2 category wins

Public leaderboard positions: Claude Sonnet 4.6 #32 (Supported); GLM-5 #28 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Sonnet 4.6 and GLM-5 share 25 comparable benchmark results. 4 of 8 categories are comparable. 8 results are unique to Claude Sonnet 4.6; 24 to GLM-5.

Updated July 20, 2026
Shared results
25
Claude Sonnet 4.6 only
8
GLM-5 only
24
Comparable categories
4 / 8

Pick GLM-5 if you want the stronger benchmark profile. Claude Sonnet 4.6 only becomes the better choice if agentic is the priority.

Confidence note. This is a partial-evidence comparison with 25 shared benchmark results across 7 evidence categories; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

GLM-5 has the cleaner BenchAlign overall profile here, landing at 66.06 versus 65.07. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

GLM-5's sharpest advantage is in mathematics, where it averages 56.3 against 26.4. The single biggest benchmark swing on the page is SuperGPQA, 95% to 66.8%. Claude Sonnet 4.6 does hit back in agentic, so the answer changes if that is the part of the workload you care about most.

Claude Sonnet 4.6 is also the more expensive model on tokens at $3.00 input / $15.00 output per 1M tokens, versus $1.00 input / $3.20 output per 1M tokens for GLM-5. That is roughly 4.7x on output cost alone.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Claude Sonnet 4.6 and GLM-5
CategoryClaude Sonnet 4.6ΔGLM-5
MathClaude Sonnet 4.626.4Margin→ 29.9GLM-556.3
AgenticClaude Sonnet 4.665.2Margin← 9.0GLM-556.2
CodingClaude Sonnet 4.669.1Margin← 2.8GLM-566.3
KnowledgeClaude Sonnet 4.666.0Margin→ 0.4GLM-566.4
ReasoningClaude Sonnet 4.6Not measuredMarginNo overlapGLM-560.8
MultilingualClaude Sonnet 4.6Not measuredMarginNo overlapGLM-583.1
MultimodalClaude Sonnet 4.677.4MarginNo overlapGLM-5Not measured
Inst. FollowingClaude Sonnet 4.6Not measuredMarginNo overlapGLM-592.6

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Claude Sonnet 4.6B · GLM-5

  1. SuperGPQA

    Knowledge
    Source ↗
    A 95%B 66.8%
    Winner: Claude Sonnet 4.6Δ 28.2
    SuperGPQA: Claude Sonnet 4.6 scored 95%; GLM-5 scored 66.8%. Claude Sonnet 4.6 wins this benchmark.

  2. FrontierMath v2 (Tiers 1-3)

    Math
    Source ↗
    A 32.400%B 16.434%
    Winner: Claude Sonnet 4.6Δ 16
    FrontierMath v2 (Tiers 1-3): Claude Sonnet 4.6 scored 32.400%; GLM-5 scored 16.434%. Claude Sonnet 4.6 wins this benchmark.

  3. MMLU-Pro

    Knowledge
    Source ↗
    A 79.2%B 85.7%
    Winner: GLM-5Δ 6.5
    MMLU-Pro: Claude Sonnet 4.6 scored 79.2%; GLM-5 scored 85.7%. GLM-5 wins this benchmark.

  4. FrontierMath v2 (Tier 4)

    Math
    Source ↗
    A 8.300%B 2.100%
    Winner: Claude Sonnet 4.6Δ 6.2
    FrontierMath v2 (Tier 4): Claude Sonnet 4.6 scored 8.300%; GLM-5 scored 2.100%. Claude Sonnet 4.6 wins this benchmark.

  5. GPQA

    Knowledge
    Source ↗
    A 89.9%B 86%
    Winner: Claude Sonnet 4.6Δ 3.9
    GPQA: Claude Sonnet 4.6 scored 89.9%; GLM-5 scored 86%. Claude Sonnet 4.6 wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricClaude Sonnet 4.6GLM-5Comparison
Input / output priceUSD per 1M tokensClaude Sonnet 4.6$3 input / $15 outputGLM-5$1 input / $3.2 outputGLM-5 has the lower combined listed price.
Generation speedtokens per secondClaude Sonnet 4.644 tok/sGLM-574 tok/sGLM-5 has the higher measured throughput.
First-answer latencyseconds to first tokenClaude Sonnet 4.61.48 sGLM-51.64 sClaude Sonnet 4.6 reaches the first token sooner.
Context windowmaximum listed tokensClaude Sonnet 4.6200KGLM-5200KListed context windows are equal.

Benchmark Deep Dive

AgenticClaude Sonnet 4.6 wins
BenchmarkClaude Sonnet 4.6GLM-5Result
Terminal-Bench 2.0Source 59.1%56.2%Claude Sonnet 4.6 leads
OSWorld-VerifiedSource 72.1%—Not comparable
Claw-EvalSource 67.8%57.7%Claude Sonnet 4.6 leads
CyberGymSource 65.2%43.2%Claude Sonnet 4.6 leads
τ²-bench resultsSource 79.5%98.2%GLM-5 leads
Gert LabsSource 62.92%50.99%Claude Sonnet 4.6 leads
OSWorld 2.0Source 8.3%—Not comparable
JobBenchSource 36.9%—Not comparable
QwenClawBenchSource —54.1%Not comparable
τ³-bench resultsSource —65.6%Not comparable
DeepPlanningSource —14.6%Not comparable
ToolathlonSource —38%Not comparable
MCP AtlasSource —31.1%Not comparable
MCP-TasksSource —60.8%Not comparable
WideResearchSource —69.8%Not comparable
APEX-Agents-AASource —14.5%Not comparable
CodingClaude Sonnet 4.6 wins
BenchmarkClaude Sonnet 4.6GLM-5Result
SWE-bench VerifiedSource 79.6%77.8%Claude Sonnet 4.6 leads
SWE-RebenchSource 60.7%62.8%GLM-5 leads
React Native EvalsSource 80.6%74.8%Claude Sonnet 4.6 leads
Vibe Code BenchSource 51.48%—Not comparable
cursorBench31Source 48.8%—Not comparable
AA-SciCodeSource 46.9%46.2%Claude Sonnet 4.6 leads
FrontierCode 1.1 MainSource 24.3%—Not comparable
SWE-bench Verified*Source —72.8%Not comparable
SWE-bench ProSource —55.1%Not comparable
SWE MultilingualSource —73.3%Not comparable
Reasoning
BenchmarkClaude Sonnet 4.6GLM-5Result
AA-LCRSource 57.7%63.3%GLM-5 leads
CritPtSource 0.9%2.0%GLM-5 leads
LongBench v2Source —60.8%Not comparable
AI-NeedleSource —63.3%Not comparable
KnowledgeGLM-5 wins
BenchmarkClaude Sonnet 4.6GLM-5Result
GPQASource 89.9%86%Claude Sonnet 4.6 leads
SuperGPQASource 95%66.8%Claude Sonnet 4.6 leads
MMLU-ProSource 79.2%85.7%GLM-5 leads
HLESource 49%50.4%GLM-5 leads
Artificial Analysis Intelligence IndexSource 35.9%39.5%GLM-5 leads
AA-GPQA DiamondSource 79.9%82.0%GLM-5 leads
AA-HLESource 13.2%27.2%GLM-5 leads
AA-Omniscience IndexSource -2.9%2.0%GLM-5 leads
AA-Omniscience AccuracySource 38.0%26.9%Claude Sonnet 4.6 leads
AA-Omniscience Hallucination RateSource 65.9%34.0%GLM-5 leads
GPQA-DSource —86.0%Not comparable
MMLU-Pro (Arcee)Source —85.8%Not comparable
MathGLM-5 wins
BenchmarkClaude Sonnet 4.6GLM-5Result
FrontierMath v2 (Tiers 1-3)Source 32.400%16.434%Claude Sonnet 4.6 leads
FrontierMath v2 (Tier 4)Source 8.300%2.100%Claude Sonnet 4.6 leads
AIME26Source —95.8%Not comparable
AIME25 (Arcee)Source —93.3%Not comparable
HMMT Feb 2025Source —97.5%Not comparable
HMMT Nov 2025Source —96.9%Not comparable
HMMT Feb 2026Source —86.4%Not comparable
MMAnswerBenchSource —82.5%Not comparable
Multilingual
BenchmarkClaude Sonnet 4.6GLM-5Result
MMLU-ProXSource —83.1%Not comparable
NOVA-63Source —55.1%Not comparable
Multimodal
BenchmarkClaude Sonnet 4.6GLM-5Result
CharXivSource 77.4%—Not comparable
AA-MMMU-ProSource 70.6%—Not comparable
Design Arena WebsiteSource 13171280Claude Sonnet 4.6 leads
Inst. Following
BenchmarkClaude Sonnet 4.6GLM-5Result
AA-IFBenchSource 41.2%72.3%GLM-5 leads
IFEvalSource —92.6%Not comparable
Frequently Asked Questions (5)

Which is better, Claude Sonnet 4.6 or GLM-5?

GLM-5 is ahead on BenchLM's BenchAlign leaderboard, 66.06 to 65.07. The biggest single separator in this matchup is SuperGPQA, where the scores are 95% and 66.8%.

Which is better for knowledge tasks, Claude Sonnet 4.6 or GLM-5?

GLM-5 has the edge for knowledge tasks in this comparison, averaging 66.4 versus 66. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.

Which is better for coding, Claude Sonnet 4.6 or GLM-5?

Claude Sonnet 4.6 has the edge for coding in this comparison, averaging 69.1 versus 66.3. Inside this category, React Native Evals is the benchmark that creates the most daylight between them.

Which is better for math, Claude Sonnet 4.6 or GLM-5?

GLM-5 has the edge for math in this comparison, averaging 56.3 versus 26.4. Inside this category, FrontierMath v2 (Tiers 1-3) is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Claude Sonnet 4.6 or GLM-5?

Claude Sonnet 4.6 has the edge for agentic tasks in this comparison, averaging 65.2 versus 56.2. Inside this category, CyberGym is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

Anthropic Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 20, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.