Z.ai, released Feb 12, 2026
GLM-5price, context, benchmarks and release details
Provisional: not enough results to rank yet Open weights 90% confidence 90 percent, High confidence, 5 of 8 expected sources in
59.4
SI Score
#65 of 142 ranked models
- Input, per 1M tokens
- $1.00Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - Output, per 1M tokens
- $3.20Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - Context window
- 205Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - Max output
- 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - Released
- Feb 12, 2026models.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗
How the score breaks down
Coding (weight 40 percent) 72.4
Math (weight 15 percent) 80.0
Preference (weight 15 percent) 77.4
Reasoning (weight 30 percent) 35.0
Weights: reasoning 30%, math 15%, coding 40%, preference 15%. Results use fixed 0–100 scales before averaging, and thin evidence is pulled toward 50. Method si-v3-retained-evidence-2, computed Oct 9, 2026, 06:15 UTC.
Around it on the leaderboard
- 63 Qwen3.5 Flash 59.5
- 64 Claude Haiku 5.5 59.4
- 65 GLM-5 59.4
- 66 Kimi K2.5 59.0
- 67 Qwen3.7 Max 58.6
Benchmark results
8 benchmarks, 10 resultsEach row shows the best published result. Where a model was tested at several settings, such as reasoning effort, open the row to see each one. Hover or tap a value for its source.
ARC-AGI-1 (public eval)reasoning 58.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] glm-5Published Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ 58.6
Open source ↗ 58.6
ARC-AGI-1 (semi-private)reasoning 44.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] glm-5Published Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ 44.7
Open source ↗ 44.7
ARC-AGI-2 (public eval)reasoning 5.4%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] glm-5Published Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ 5.4
Open source ↗ 5.4
ARC-AGI-2 (semi-private)reasoning 4.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] glm-5Published Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ 4.9
Open source ↗ 4.9
GPQA Diamondreasoning 87.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 12, 2026
Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 87.8
Open source ↗ 87.8
OTIS Mock AIME 2024–2025math 80%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 12, 2026
Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 80.0
Open source ↗ 80.0
SWE-bench Verifiedcoding 72.8%Official model cards via models.devLab-reported; metric resolved; transcribed by MIT models.dev catalog; not independently evaluated [variant]
Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗
72.8 3 settings
- Setting 1 72.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 15, 2026
Retrieved Oct 9, 2026 · CC-BY
Open source ↗ - Setting 2 72.8%Official model cards via models.devLab-reported; metric resolved; transcribed by MIT models.dev catalog; not independently evaluated [variant]
Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ - Setting 3 72.8%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] mini-SWE-agent; high; 2.0.0Published Feb 17, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
LMArena Textpreference 1446.2 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026
Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 77.4
Open source ↗ 77.4
Normalization uses a fixed 0–100 scale for each unit, independent of other models. Compare evaluation conditions before reading a small gap as decisive. “Lab-reported” marks the provider's own published figure.
Details and sources
- Open weights
- YesHugging Face HubPublic Hub repo with weight files; gating/repo upload date is not release date
Retrieved Oct 9, 2026 · factual metadata; model-specific licenses
Open source ↗ - License
- mitHugging Face HubPublished source fact
Retrieved Oct 9, 2026 · factual metadata; model-specific licenses
Open source ↗ - Input modalities
- textmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - First seen by SuperIndex
- Oct 8, 2026
- Coverage
- 72% of expected source weight
Reported (5)
- ARC PrizeOct 8, 2026
- Epoch AI BenchmarkingOct 8, 2026
- Official model cards via models.devOct 8, 2026
- LMArena / ArenaOct 8, 2026
- SWE-bench VerifiedOct 8, 2026
Awaiting (3)
- Humanity’s Last Exam11% of weight
- LiveBench11% of weight
- Terminal-Bench6% of weight
Confidence rises as pending sources publish. Some sources never cover some models, so confidence reaches 100% at 80% of expected weight.