GoogleGemma 4 E2B
Gemma 4 E2B is a Google open-weights reasoning model, released 2 Apr 2026. Its best configuration (thinking reasoning effort) ranks #624 of 785 on the BenchLeader Index at 41.6 ±5.2, in the lower half. The ± is the point: 308 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in knowledge (51) and lowest in multimodal (27). At $0.050 per million tokens blended it is among the cheapest fifth of ranked models. It has been measured at 3 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 2 Apr 2026.stale: no new result in six months
- Blended price
- $0.050/M
- $0.040 in · $0.080 out
- Output speed
- –
- First answer
- –
- Context
- 131k
- Full answer
- –
- Cost per run
- –
- Released
- 2 Apr 2026
- Overall index42
- Reasoning41
- Agents & tools36
- Knowledge51
- Instruction following41
- Multimodal27
- Long context32
- Composite38
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| no reasoning | 39.1 | #696 | – | – | $0.0000 | Agents & tools 36 · Composite 37 · Instruction following 37 · Knowledge 34 · Long context 32 · Multimodal 24 · Reasoning 41 |
| thinkingbest | 41.6 | #624 | – | – | $0.0000 | Agents & tools 36 · Composite 38 · Instruction following 41 · Knowledge 51 · Long context 32 · Multimodal 27 · Reasoning 41 |
| not stated | – | – | – | – | $0.0000 |
How its index has moved
9 Sept 2026 to 21 Oct 2026- thinking
- no reasoning
The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | no reasoning | thinking | Source |
|---|---|---|---|
| GPQA Diamond (AA)not in index | 40.5%#477 | 43.3%#458 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 4.7%#477 | 4.8%#475 | Artificial Analysis |
| CritPt | 0.0%#315 | 0.0%#315 | Artificial Analysis |
Coding
| Benchmark | thinking | Source |
|---|---|---|
| Terminal-Bench 2.1 (AA)not in index | 0.4%#228 | Artificial Analysis |
Agents & tools
| Benchmark | no reasoning | thinking | Source |
|---|---|---|---|
| Terminal-Bench Hard | 2.3%#320 | 3.0%#314 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 22.2%#314 | 20.8%#329 | Artificial Analysis |
| GDPval-AA v2.1not in index | – | 0.0%#124 | Artificial Analysis |
Knowledge
| Benchmark | no reasoning | thinking | Source |
|---|---|---|---|
| AA-Omniscience | -60.2#467 | -23.6#258 | Artificial Analysis |
| AA-Omniscience: accuracynot in index | 8.2%#518 | 6.6%#533 | Artificial Analysis |
| AA-Omniscience: non-hallucinationnot in index | 25.6%#240 | 67.6%#53 | Artificial Analysis |
Instruction following
| Benchmark | no reasoning | thinking | Source |
|---|---|---|---|
| IFBench | 33.6%#325 | 38.0%#286 | Artificial Analysis |
Multimodal
| Benchmark | no reasoning | thinking | not stated | Source |
|---|---|---|---|---|
| MMMU-Pro | 41.8%#263 | 44.6%#255 | – | Artificial Analysis |
| MMMU-Pro (official)not in indexeffort not stated | – | – | 44.2%#21 | MMMU |
Long context
| Benchmark | no reasoning | thinking | Source |
|---|---|---|---|
| AA-LCR | 16.3%#449 | 16.3%#449 | Artificial Analysis |
Composite
| Benchmark | no reasoning | thinking | Source |
|---|---|---|---|
| AA Intelligence Index v4.3.2 | 6.5#525 | 7.8#458 | Artificial Analysis |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0000 | – | – |
| Summarize a 30-page report | 12,000 / 600 | $0.0005 | – | – |
| Code edit | 6,000 / 1,500 | $0.0004 | – | – |
| Agentic coding session | 60,000 / 4,000 | $0.0027 | – | – |
| Structured extraction | 2,000 / 200 | $0.0001 | – | – |
More from Google
See also
Questions people ask
- What are Gemma 4 E2B's benchmark scores?
- As of 24 Oct 2026, Gemma 4 E2B (thinking effort) scores 41.6 ±5.2 on the BenchLeader Index, strongest in knowledge (51) and weakest in multimodal (27). That rests on 7 independent benchmark results, and every score on this page links to its publisher.
- How does Gemma 4 E2B rank?
- Gemma 4 E2B (thinking effort) is #624 of 785 ranked configurations on 24 Oct 2026. 308 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Gemma 4 E2B cost per 1M tokens?
- As of 24 Oct 2026, Gemma 4 E2B costs $0.040 per 1M input tokens and $0.080 per 1M output tokens, $0.050 blended (three input tokens per output token).
- When was Gemma 4 E2B released?
- Google released Gemma 4 E2B on 2 Apr 2026. BenchLeader has results for it at 3 reasoning-effort settings.
Data as of 24 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “Gemma 4 E2B: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/gemma-4-e2b.