Model comparison
GLM-4.5-Air vs Mistral Large 2
Head-to-head evidence from 11 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GLM-4.5-Air #133 (Supported); Mistral Large 2 #163 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GLM-4.5-Air and Mistral Large 2 share 11 comparable benchmark results. 0 of 8 categories are comparable. 1 result is unique to GLM-4.5-Air; 0 to Mistral Large 2.
Updated July 20, 2026- Shared results
- 11
- GLM-4.5-Air only
- 1
- Mistral Large 2 only
- 0
- Comparable categories
- 0 / 8
Benchmark data for GLM-4.5-Air and Mistral Large 2 is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 11 shared benchmark results across 5 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GLM-4.5-Air | Mistral Large 2 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GLM-4.5-Air$0.2 input / $1.1 output | Mistral Large 2Not available | A complete price comparison is not available. |
| Generation speedtokens per second | GLM-4.5-Air106 tok/s | Mistral Large 238 tok/s | GLM-4.5-Air has the higher measured throughput. |
| First-answer latencyseconds to first token | GLM-4.5-Air1.18 s | Mistral Large 21.45 s | GLM-4.5-Air reaches the first token sooner. |
| Context windowmaximum listed tokens | GLM-4.5-Air128K | Mistral Large 2128K | Listed context windows are equal. |
Benchmark Deep Dive
Agentic1 benchmarks
| Benchmark | GLM-4.5-Air | Mistral Large 2 | Result |
|---|---|---|---|
| τ²-bench resultsSource | 46.5% | 30.7% | GLM-4.5-Air leads |
Coding1 benchmarks
| Benchmark | GLM-4.5-Air | Mistral Large 2 | Result |
|---|---|---|---|
| AA-SciCodeSource | 30.6% | 29.2% | GLM-4.5-Air leads |
Reasoning2 benchmarks
Knowledge6 benchmarks
| Benchmark | GLM-4.5-Air | Mistral Large 2 | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 16.5% | 9.2% | GLM-4.5-Air leads |
| AA-GPQA DiamondSource | 73.3% | 48.6% | GLM-4.5-Air leads |
| AA-HLESource | 6.8% | 4.0% | GLM-4.5-Air leads |
| AA-Omniscience IndexSource | -62.5% | -34.0% | Mistral Large 2 leads |
| AA-Omniscience AccuracySource | 15.5% | 20.1% | Mistral Large 2 leads |
| AA-Omniscience Hallucination RateSource | 92.3% | 67.8% | Mistral Large 2 leads |
Multimodal1 benchmarks
| Benchmark | GLM-4.5-Air | Mistral Large 2 | Result |
|---|---|---|---|
| Design Arena WebsiteSource | 1179 | — | Not comparable |
Inst. Following1 benchmarks
| Benchmark | GLM-4.5-Air | Mistral Large 2 | Result |
|---|---|---|---|
| AA-IFBenchSource | 37.6% | 31.2% | GLM-4.5-Air leads |
Frequently Asked Questions (3)
Can I compare GLM-4.5-Air and Mistral Large 2 on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for GLM-4.5-Air and Mistral Large 2 today?
GLM-4.5-Air: $0.20 input / $1.10 output per 1M tokens Mistral Large 2: Pricing unavailable Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
Related Comparisons
Explore More
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.