Gemma 4 E2B
- Input
- —
- Output
- —
- Speed
- ~79tok/sest.
- Context
- 128Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Gemma 4 E2B (Non-reasoning). Price = AA median host price.
Rankings
Writing & chat
Verified#130 / 162rank by quality22.0±9.5quality / 1001/5 benchmarks measuredVision
Verified#88 / 98rank by quality19.1±8.2quality / 1001/6 benchmarks measuredHard reasoning
Verified#190 / 218rank by quality12.9±5.9quality / 1002/4 benchmarks measuredAgents
Verified#143 / 187rank by quality16.0±10.0quality / 1001/7 benchmarks measured
Self-hostingEstimated
How we estimate →What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.
- Hardware
- 1× B200 180GB
- BF16 weights
- Throughput
- ~19,629 tok/s
- many requests batched
- Price
- $0.035–0.32 /M tok
- busy → light use
- On your own machine
- RTX 5090 32GB (int4, 300+ tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- BF16 weights (5.1B params, 2.3B active per token) + 25% KV-cache headroom ≈ 13 GB
- 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
- ~19,629 output tok/s aggregate at batch 256 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~231,114 tok/s
- Low = 75% utilization at the low GPU price; high = 20% at the high price
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Writing & chat
IFBenchVerified
#103 of 13933.6%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #102INTELLECT-334.0%
- #103Gemma 4 E2B33.6%
- #104EXAONE 4.0 32B33.5%
artificialanalysis.ai · 2026-09-24
MMMLUEstimated
~last of 5 (estimated)below measured range (<81.3%)
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#48 of 57 (estimated)~1315 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #47INTELLECT-3Few votes1327
- ~#48Gemma 4 E2BEstimated1315
- #48Llama 4 Maverick1311
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#49 of 57 (estimated)~1339 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #48Llama 3.1 Nemotron Ultra 253B v1Few votes1348
- ~#49Gemma 4 E2BEstimated1339
- #49Olmo 3.1 32B Instruct1330
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#23 of 26 (estimated)~1384 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #22Mistral Large 31412
- ~#23Gemma 4 E2BEstimated1384
- #23Gemma 4 31B1368
No published score — estimated from related benchmarks
Vision
MMMU-ProVerified
#78 of 8741.8%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #77GLM-4.6V42.2%
- #78Gemma 4 E2B41.8%
- #79Llama 3.2 Instruct 90B (Vision)39.5%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~last of 12 (estimated)below measured range (<74.5%)
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~last of 8 (estimated)below measured range (<75.8%)
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#46 of 48 (estimated)~0.2%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #45Ministral 3 8B0.8%
- ~#46Gemma 4 E2BEstimated0.2%
- #46Ministral 3 3B0.0%
No published score — estimated from related benchmarks
ChartographyEstimated
~last of 25 (estimated)below measured range (<9.0%)
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#168 of 19240.5%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #167Kimi Linear 48B A3B Instruct41.2%
- #168Gemma 4 E2B40.5%
- #169Olmo 3 7B Instruct40.0%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#173 of 1984.7%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #171Nemotron 3 Nano Omni 30B A3B Reasoning4.8%
- #173Gemma 4 E2B4.7%
- #174Ministral 3 14B4.6%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#29 of 34 (estimated)~26.3%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #28Ministral 3 14B30.0%
- ~#29Gemma 4 E2BEstimated26.3%
- #29Ministral 3 3B22.0%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#100 of 103 (estimated)~5.4
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #99Ministral 3 8B5.5
- ~#100Gemma 4 E2BEstimated5.4
- #100Ministral 3 3B4.8
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#76 of 11922.2%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #74NVIDIA Nemotron Nano 9B V223.4%
- #76Gemma 4 E2B22.2%
- #76Hermes 4 - Llama-3.1 405B22.2%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#13 of 15 (estimated)~52.1%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #12Nemotron 3.5 Super VL NVFP452.3%
- ~#13Gemma 4 E2BEstimated52.1%
- #13Nemotron 3.5 Super VL51.1%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#21 of 22 (estimated)~36.0%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #20Nemotron 3 Ultra44.4%
- ~#21Gemma 4 E2BEstimated36.0%
- #21Mistral Small 421.3%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#60 of 92 (estimated)~716 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #59Claude Haiku 4.5719
- ~#60Gemma 4 E2BEstimated716
- #60MiniCPM5-2B694
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#79 of 85 (estimated)~0.3%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #77Granite 4.2 3B0.4%
- ~#79Gemma 4 E2BEstimated0.3%
- #79gpt-oss-120b0.2%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#90 of 91 (estimated)~3.4%
- #1Muse Spark 1.350.5%
- #2GLM-5.350.3%
- #88Ministral 3 8B3.7%
- ~#90Gemma 4 E2BEstimated3.4%
- #90Llama 4 Scout3.3%
No published score — estimated from related benchmarks