# GLM-4.5V

> Source: Benchize (https://benchize.com) — https://benchize.com/models/glm-4-5v. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/glm-4-5v.

Z.ai

Canonical URL: https://benchize.com/models/glm-4-5v
Last updated: Thu, 22 Oct 2026 06:20:09 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Z.ai

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Source |  |
| --- | --- | --- | --- | --- | --- | --- |
| [Kangaroo 2025 3-4](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_3-4.md) | 45.83% | 95% CI 35.86–55.8% | 16 / 16 | 0.005usd per problem | [matharena · kangaroo--kangaroo_2025_3-4](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_3-4) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 45.83 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.005 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_3-4 predicted false sourceModelName GLM 4.5V sourceModelVersion glm/glm-45v ### Reported statistics Uncertainty 95% confidence interval: 35.86–55.8% confidenceInterval95 9.97 problems 24 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_3-4) Source matharena Original model label GLM 4.5V Source version kangaroo--kangaroo_2025_3-4 Observed 2026-10-22T05:30:10.341Z Evidence SHA-256 `38fec99c55752fef6703c9ed49d9e1e204b235f2bd78d5ee47725dac9e5da89c` Source locator `/table/rows/20` |  |  |  |  |  |  |
| [ArXivMath Overall](https://benchize.com/benchmarks/matharena%3Aoverall--visual_math.md) | 67.6% | 95% CI 64.13–71.07% | 15 / 15 | 0.005usd per problem | [matharena · overall--visual_math](https://matharena.ai/competition_tables/overall--visual_math) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.60 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.005 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition overall--visual_math predicted false sourceModelName GLM 4.5V sourceModelVersion glm/glm-45v ### Reported statistics Uncertainty 95% confidence interval: 64.13–71.07% confidenceInterval95 3.47 problems Not reported ### Source [Original source](https://matharena.ai/competition_tables/overall--visual_math) Source matharena Original model label GLM 4.5V Source version overall--visual_math Observed 2026-10-22T05:30:09.818Z Evidence SHA-256 `b38d1f465012aab8b7d0930aea897d4e5be10ec02c16643c24c9251c8febb173` Source locator `/table/rows/20` |  |  |  |  |  |  |
| [Kangaroo 2025 11-12](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_11-12.md) | 78.33% | 95% CI 70.96–85.7% | 16 / 16 | 0.006usd per problem | [matharena · kangaroo--kangaroo_2025_11-12](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 78.33 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.006 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false sourceModelName GLM 4.5V sourceModelVersion glm/glm-45v ### Reported statistics Uncertainty 95% confidence interval: 70.96–85.7% confidenceInterval95 7.37 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label GLM 4.5V Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-22T05:30:11.337Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/21` |  |  |  |  |  |  |
| [Kangaroo 2025 5-6](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_5-6.md) | 62.5% | 95% CI 53.84–71.16% | 13 / 16 | 0.005usd per problem | [matharena · kangaroo--kangaroo_2025_5-6](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_5-6) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 62.50 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.005 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_5-6 predicted false sourceModelName GLM 4.5V sourceModelVersion glm/glm-45v ### Reported statistics Uncertainty 95% confidence interval: 53.84–71.16% confidenceInterval95 8.66 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_5-6) Source matharena Original model label GLM 4.5V Source version kangaroo--kangaroo_2025_5-6 Observed 2026-10-22T05:30:10.589Z Evidence SHA-256 `9460cafccce0b6f3ba1f90e1090be31d6cf94dd10b9157819abc97efe624b126` Source locator `/table/rows/18` |  |  |  |  |  |  |
| [Kangaroo 2025 1-2](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_1-2.md) | 65.62% | 95% CI 56.12–75.12% | 11 / 16 | 0.004usd per problem | [matharena · kangaroo--kangaroo_2025_1-2](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_1-2) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65.62 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.004 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_1-2 predicted false sourceModelName GLM 4.5V sourceModelVersion glm/glm-45v ### Reported statistics Uncertainty 95% confidence interval: 56.12–75.12% confidenceInterval95 9.50 problems 24 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_1-2) Source matharena Original model label GLM 4.5V Source version kangaroo--kangaroo_2025_1-2 Observed 2026-10-22T05:30:10.078Z Evidence SHA-256 `a59a4c362e2d87350330706a01dd330e9a1ac7cc64a4de0bacbf1a439d8fcf90` Source locator `/table/rows/13` |  |  |  |  |  |  |
| [Kangaroo 2025 9-10](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_9-10.md) | 78.33% | 95% CI 70.96–85.7% | 15 / 15 | 0.005usd per problem | [matharena · kangaroo--kangaroo_2025_9-10](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_9-10) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 78.33 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.005 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_9-10 predicted false sourceModelName GLM 4.5V sourceModelVersion glm/glm-45v ### Reported statistics Uncertainty 95% confidence interval: 70.96–85.7% confidenceInterval95 7.37 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_9-10) Source matharena Original model label GLM 4.5V Source version kangaroo--kangaroo_2025_9-10 Observed 2026-10-22T05:30:11.076Z Evidence SHA-256 `52964b89ab1a06cf2e79ec946b33004aa40ca31f1ec26888e6dd0f0a7994223a` Source locator `/table/rows/21` |  |  |  |  |  |  |
| [Kangaroo 2025 7-8](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_7-8.md) | 75% | 95% CI 67.25–82.75% | 15 / 15 | 0.005usd per problem | [matharena · kangaroo--kangaroo_2025_7-8](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_7-8) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.005 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_7-8 predicted false sourceModelName GLM 4.5V sourceModelVersion glm/glm-45v ### Reported statistics Uncertainty 95% confidence interval: 67.25–82.75% confidenceInterval95 7.75 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_7-8) Source matharena Original model label GLM 4.5V Source version kangaroo--kangaroo_2025_7-8 Observed 2026-10-22T05:30:10.837Z Evidence SHA-256 `197887eb5244aa6bce3570bd9eb25bbb0bb6ec95568339536d94e2859f0ee8c1` Source locator `/table/rows/21` |  |  |  |  |  |  |

---
Cite as: GLM-4.5V — Benchize, https://benchize.com/models/glm-4-5v (retrieved 2026-10-22)