# Kangaroo 2025 11-12 > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_11-12. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_11-12. Kangaroo 2025 11-12: Mathematical reasoning on school-level multiple-choice problems, including visual diagrams and patterns. This competition contains 30 problems. MathArena reports normalized performance across repeated attempts and a 95% confidence interval. Canonical URL: https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_11-12 Last updated: Wed, 21 Oct 2026 18:52:20 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Conquered Kangaroo 2025 11-12: Mathematical reasoning on school-level multiple-choice problems, including visual diagrams and patterns. This competition contains 30 problems. MathArena reports normalized performance across repeated attempts and a 95% confidence interval. Mathematics · Models tested: 16 · Score publishers: [matharena](https://matharena.ai/?comp=kangaroo--kangaroo_2025_11-12) ## Model results | # | Model | Score | ± | Cost | | | --- | --- | --- | --- | --- | --- | | 1 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max | 100% | 95% CI 100–100% | 0.19usd per problem | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.19 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false Reasoning effort max sourceModelName Claude-Opus-4.8 (max) sourceModelVersion anthropic/opus_48_max thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 100–100% confidenceInterval95 0.00 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label Claude-Opus-4.8 (max) Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/0` | | | | | | | 2 | [GPT-5.4](https://benchize.com/models/gpt-5-4-xhigh.md)Extra high | 98.33% | 95% CI 96.04–100.62% | 0.08usd per problem | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 98.33 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.079 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false Reasoning effort xhigh sourceModelName GPT-5.4 (xhigh) sourceModelVersion openai/gpt-54 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 96.04–100.62% confidenceInterval95 2.29 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label GPT-5.4 (xhigh) Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/2` | | | | | | | 2 | [GPT-5.5](https://benchize.com/models/gpt-5-5-xhigh.md)Extra high | 98.33% | 95% CI 96.04–100.62% | 0.09usd per problem | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 98.33 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.09 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false Reasoning effort xhigh sourceModelName GPT-5.5 (xhigh) sourceModelVersion openai/gpt-55 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 96.04–100.62% confidenceInterval95 2.29 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label GPT-5.5 (xhigh) Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/3` | | | | | | | 4 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview.md) | 97.5% | 95% CI 94.71–100.29% | 0.12usd per problem | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 97.50 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.12 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false sourceModelName Gemini 3.1 Pro Preview sourceModelVersion gemini/gemini-31-pro ### Reported statistics Uncertainty 95% confidence interval: 94.71–100.29% confidenceInterval95 2.79 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label Gemini 3.1 Pro Preview Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/5` | | | | | | | 5 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash.md) | 96.67% | 95% CI 92.13–101.21% | 0.03usd per problem | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.67 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.033 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 92.13–101.21% confidenceInterval95 4.54 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label Gemini 3.6 Flash Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/6` | | | | | | | 6 | [Gemini 3 Flash](https://benchize.com/models/gemini-3-flash.md) | 95.83% | 95% CI 92.25–99.41% | 0.03usd per problem | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.83 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.028 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false sourceModelName Gemini 3 Flash sourceModelVersion gemini/gemini-3-flash ### Reported statistics Uncertainty 95% confidence interval: 92.25–99.41% confidenceInterval95 3.58 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label Gemini 3 Flash Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/7` | | | | | | | 6 | [GPT-5.2](https://benchize.com/models/gpt-5-2-high.md)High | 95.83% | 95% CI 92.25–99.41% | 0.05usd per problem | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.83 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.053 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 92.25–99.41% confidenceInterval95 3.58 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label GPT-5.2 (high) Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/8` | | | | | | | 8 | [GPT-5](https://benchize.com/models/gpt-5-high.md)High | 95% | 95% CI 91.1–98.9% | 0.08usd per problem | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.075 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false Reasoning effort high sourceModelName GPT-5 (high) sourceModelVersion openai/gpt-5 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 91.1–98.9% confidenceInterval95 3.90 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label GPT-5 (high) Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/9` | | | | | | | 9 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash.md) | 93.33% | 95% CI 87.02–99.64% | 0.05usd per problem | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.33 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.050 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false sourceModelName Gemini 3.5 Flash sourceModelVersion gemini/gemini-35-flash ### Reported statistics Uncertainty 95% confidence interval: 87.02–99.64% confidenceInterval95 6.31 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label Gemini 3.5 Flash Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/10` | | | | | | | 10 | [Qwen3.5 397B A17B](https://benchize.com/models/qwen3-5-397b-a17b.md) | 91.67% | 95% CI 86.72–96.62% | 0.04usd per problem | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.67 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.037 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false sourceModelName Qwen3.5-397b-a17b sourceModelVersion qwen/qwen3.5_397b ### Reported statistics Uncertainty 95% confidence interval: 86.72–96.62% confidenceInterval95 4.95 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label Qwen3.5-397b-a17b Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/11` | | | | | | | 10 | [GPT-5.1](https://benchize.com/models/gpt-5-1-high.md)High | 91.67% | 95% CI 86.72–96.62% | 0.08usd per problem | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.67 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.075 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false Reasoning effort high sourceModelName GPT-5.1 (high) sourceModelVersion openai/gpt-51 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 86.72–96.62% confidenceInterval95 4.95 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label GPT-5.1 (high) Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/12` | | | | | | | 12 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 89.17% | 95% CI 83.61–94.73% | 0.11usd per problem | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.17 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.11 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false sourceModelName Gemini 2.5 Pro sourceModelVersion gemini/gemini-pro-2.5 ### Reported statistics Uncertainty 95% confidence interval: 83.61–94.73% confidenceInterval95 5.56 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label Gemini 2.5 Pro Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/14` | | | | | | | 13 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6-high.md)High | 87.5% | 95% CI 81.58–93.42% | 0.21usd per problem | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.50 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.21 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false Reasoning effort high sourceModelName Claude-Opus-4.6 (High) sourceModelVersion anthropic/opus_46 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 81.58–93.42% confidenceInterval95 5.92 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label Claude-Opus-4.6 (High) Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/16` | | | | | | | 14 | [Qwen3 VL 235B A22B Instruct](https://benchize.com/models/qwen3-vl-235b-a22b-instruct.md) | 85.83% | 95% CI 79.59–92.07% | 0.01usd per problem | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.83 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.010 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false sourceModelName Qwen3-VL-235B Instruct sourceModelVersion qwen/qwen3_vl_235b_a22b_instruct ### Reported statistics Uncertainty 95% confidence interval: 79.59–92.07% confidenceInterval95 6.24 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label Qwen3-VL-235B Instruct Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/17` | | | | | | | 15 | [GPT-5 Mini](https://benchize.com/models/gpt-5-mini-high.md)High | 85% | 95% CI 78.61–91.39% | 0.01usd per problem | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.011 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false Reasoning effort high sourceModelName GPT-5-mini (high) sourceModelVersion openai/gpt-5-mini thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 78.61–91.39% confidenceInterval95 6.39 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label GPT-5-mini (high) Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/18` | | | | | | | 16 | [GLM-4.5V](https://benchize.com/models/glm-4-5v.md) | 78.33% | 95% CI 70.96–85.7% | 0.006usd per problem | | | ### 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 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/21` | | | | | | --- Cite as: Kangaroo 2025 11-12 — Benchize, https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_11-12 (retrieved 2026-10-21)